BLEU

The main goal of this paper is to pro- pose automatic schemes for the trans- lation paired comparison method. This method was proposed to precisely eval- uate a speech translation …...

Following the recent adoption by the machine translation community of automatic evalua- tion using the BLEU/NIST scoring process, we conduct an in-depth study of a similar idea for evaluating summaries. …...

When rules of transfer-based machine translation (MT) are automatically ac- quired from bilingual corpora, incor- rect/redundant rules are generated due to acquisition errors or translation variety in the corpora. As …...

Based upon a statistically trained speech translation system, in this study, we try to combine distinctive features derived from the two modules: speech recognition and statistical machine translation, in a …...

This paper describes the application of discrim- inative reranking techniques to the problem of machine translation. For each sentence in the source language, we obtain from a baseline sta- tistical …...

In this paper we report on the results of an experiment in designing resource-light metrics that predict the potential translation complexity of a text or a corpus of homogenous texts …...

We present the results of an experiment on extending the automatic method of Machine Translation evaluation BLUE with statistical weights for lexical items, such as tf.idf scores. We show that …...

We present a statistical phrase-based transla- tion model that uses hierarchical phrases— phrases that contain subphrases. The model is formally a synchronous context-free gram- mar but is learned from a …...

We designed, implemented and assessed ALEPH, a pure example-based machine translation system. It strictly does not make any use of variables, templates or training, does not have any explicit transfer …...

Syntax-based statistical machine transla- tion (MT) aims at applying statistical models to structured data. In this paper, we present a syntax-based statistical ma- chine translation system based on a prob- …...

In this paper, we present a novel distortion model for phrase-based statistical machine translation. Unlike the pre- vious phrase distortion models whose role is to simply penal- ize nonmonotonic alignments[1, …...

This paper considers the popular but ques- tionable technique of ‘round-trip transla- tion’ (RTT) as a means of evaluating free on-line Machine Translation systems. Two experiments are reported, both relat- …...

AbstractWe examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments. Translation Edit Rate (TER) measures …...

AbstractAs an approach to syntax based statistical machine translation (SMT), Probabilistic Synchronous Dependency Insertion Grammars (PSDIG), introduced in (Ding and Palmer, 2005), are a version of synchronous grammars defined on …...

We consider the evaluation problem in Natural Language Generation (NLG) and present results for evaluating several NLG systems with similar functionality, includ- ing a knowledge-based generator and sev- eral statistical …...

This paper describes a novel method for computing a consensus translation from the outputs of multiple machine trans- lation (MT) systems. The outputs are combined and a possibly new transla- …...

AbstractInflected languages in a low-resource setting present a data sparsity problem for statistical machine translation. In this paper, we present a minimally supervised algorithm for morpheme segmentation on Arabic dialects …...

We discuss different strategies for smooth- ing the phrasetable in Statistical MT, and give results over a range of translation set- tings. We show that any type of smooth- ing …...

We introduce SPMT, a new class of sta- tistical Translation Models that use Syn- tactified target language Phrases. The SPMT models outperform a state of the art phrase-based baseline model …...

AbstractTransBooster is a wrapper technology designed to improve the performance of wide-coverage machine translation systems. Using linguistically motivated syntactic information, it automatically decomposes source language sentences into shorter and syntactically …...

Syntactic reordering approaches are an ef- fective method for handling word-order dif- ferences between source and target lan- guages in statistical machine translation (SMT) systems. This paper introduces a re- …...

We investigate different representational granularities for sub-lexical representation in statistical machine translation work from English to Turkish. We find that (i) rep- resenting both Turkish and English at the morpheme-level …...

AbstractInspired by previous chunk-level reordering approaches to statistical machine translation, this paper presents two methods to improve the reordering at the chunk level. By introducing a new lattice weighting factor …...

Recently, confusion network decoding has been applied in machine translation system combination. Due to errors in the hypoth- esis alignment, decoding may result in un- grammatical combination outputs. This pa- …...

Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation es- timates and low coverage over source and target phrases. This paper …...

We propose a novel syntax-based model for statistical machine translation in which meta-structure (MS) and meta-structure se- quence (SMS) of a parse tree are defined. In this framework, a parse …...

Meteor is an automatic metric for Ma- chine Translation evaluation which has been demonstrated to have high levels of corre- lation with human judgments of translation quality, significantly outperforming the …...

We address the problem of smoothing trans- lation probabilities in a bilingual N-gram- based statistical machine translation system. It is proposed to project the bilingual tuples onto a continuous space …...

AbstractOur statistical machine translation system that uses large Japanese-English parallel sentences and long phrase tables is described. We collected 698,973 Japanese-English parallel sentences, and we used long phrase tables. Also, …...

AbstractThis paper is a description of the system presented by the LIG laboratory to the IWSLT07 speech translation evaluation. The LIG participated, for the first time this year, in the …...

This paper proposes a method using the ex- isting Rule-based Machine Translation (RBMT) system as a black box to produce synthetic bilingual corpus, which will be used as training data …...

In this paper, we present a Bayesian Learn- ing based method to train word dependent transition models for HMM based word alignment. We present word alignment re- sults on the …...

The treatment of ‘spurious’ words of source language is an important problem but often ignored in the discussion on phrase-based SMT. This paper explains why it is impor- tant and …...

Confusion networks are a simple representa- tion of multiple speech recognition or transla- tion hypotheses in a machine translation sys- tem. A typical operation on a confusion net- work is …...

Among syntax-based translation models, the tree-based approach, which takes as input a parse tree of the source sentence, is a promis- ing direction being faster and simpler than its string-based …...

Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bi- text. The current …...

The state-of-the-art system combination method for machine translation (MT) is the word-based combination using confu- sion networks. One of the crucial steps in confusion network decoding is the align- ment …...

Minimum error rate training (MERT) is a widely used learning procedure for statistical machine translation models. We contrast three search strategies for MERT: Powell’s method, the variant of coordinate descent …...

Many reordering approaches have been proposed for the statistical machine translation (SMT) system. However, the information about the type of source sentence is ignored in the previous works. In this …...

An important problem in translation neglected by most recent statistical machine translation systems is insertion and deletion of words, such as function words, motivated by linguistic structure rather than adjacent …...

Translation model size is growing at a pace that outstrips improvements in computing power, and this hinders research on many interesting models. We show how an al- gorithmic scaling technique …...

We show that jointly parsing a bitext can sub- stantially improve parse quality on both sides. In a maximum entropy bitext parsing model, we define a distribution over source trees, …...

Based on an architecture that allows to com- bine statistical machine translation (SMT) with rule-based machine translation (RBMT) in a multi-engine setup, we present new results that show that this …...

Reordering is a serious challenge in sta- tistical machine translation. We propose a method for analysing syntactic reorder- ing in parallel corpora and apply it to un- derstanding the differences …...

We present a series of empirical studies aimed at illuminating more precisely the likely contribution of semantic roles in im- proving statistical machine translation ac- curacy. The experiments reported study …...

We propose a novel objective function for dis- criminatively tuning log-linear machine trans- lation models. Our objective explicitly op- timizes the BLEU score of expected n-gram counts, the same quantities …...

Linking constructions involving � (DE) are ubiq- uitous in Chinese, and can be translated into En- glish in many different ways. This is a major source of machine translation error, …...

In this work, we propose two extensions of standard word lexicons in statistical ma- chine translation: A discriminative word lexicon that uses sentence-level source in- formation to predict the target …...

Manual evaluation of translation quality is generally thought to be excessively time consuming and expensive. We explore a fast and inexpensive way of doing it using Amazon’s Mechanical Turk to …...

Current phrase-based statistical machine translation systems process each test sentence in isolation and do not enforce global consis- tency constraints, even though the test data is often internally consistent with …...

We present a method to align words in a bitext that combines elements of a tra- ditional statistical approach with linguis- tic knowledge. We demonstrate this ap- proach for Arabic-English, …...

We describe the LIU systems for English- German and German-English translation in the WMT09 shared task. We focus on two methods to improve the word align- ment: (i) by applying …...

-like text summarisation requires a means of producing novel summary sen- tences. In order to improve the grammati- cality of the generated sentence, we model a global (sentence) level syntactic …...

This paper describes the incremental hy- pothesis alignment algorithm used in the BBN submissions to the WMT09 system combination task. The alignment algo- rithm used a sentence specific alignment order, …...

We describe a synthetic method for com- bining machine translations produced by different systems given the same input. One-best outputs are explicitly aligned to remove duplicate words. Hypotheses follow system …...

We present a new phrase-based con- ditional exponential family translation model for statistical machine translation. The model operates on a feature repre- sentation in which sentence level transla- tions are …...

We explored novel automatic evaluation measures for machine translation output oriented to the syntactic structure of the sentence: the BLEU score on the detailed Part-of-Speech (POS) tags as well as …...

This paper introduces a new statistical pre- processing model for Rule-Based Machine Translation (RBMT) systems. We train a Statistical Machine Translation (SMT) system using monolingual corpora. This model can transform …...

A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend phrase-based decoding to allow both source …...

AbstractIn Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an important first step in …...

This paper describes the Aalto submission for the German-to-English and the Czech- to-English translation tasks of the ACL 2010 Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR. Statistical machine …...

Automatic evaluation of Machine Translation (MT) quality is essential to developing high- quality MT systems. Various evaluation met- rics have been proposed, and BLEU is now used as the de …...

This paper describes our submission, cmu-heafield-combo, to the WMT 2010 machine translation system combi- nation task. Using constrained resources, we participated in all nine language pairs, namely translating English to …...

Word alignment plays a central role in statisti- cal MT (SMT) since almost all SMT systems extract translation rules from word aligned parallel training data. While most SMT systems use …...

We present a constituent parsing-based reordering technique that improves the performance of the state-of-the-art Eng- lish-to-Japanese phrase translation sys- tem that includes distortion models by 4.76 BLEU points. The phrase …...

This paper proposes a novel method for long distance, clause-level reordering in statistical machine translation (SMT). The proposed method separately translates clauses in the source sentence and recon- structs the …...

This paper presents a fast consensus hy- pothesis regeneration approach for ma- chine translation. It combines the advan- tages of feature-based fast consensus de- coding and hypothesis regeneration. Our approach …...

This study evaluates the impact of inte- grating two different collocation segmen- tations methods in a standard phrase-based statistical machine translation approach. The collocation segmentation techniques are implemented simultaneously in …...

Syntactic machine translation systems extract rules from bilingual, word-aligned, syntacti- cally parsed text, but current systems for pars- ing and word alignment are at best cascaded and at worst totally …...

Tree-based translation models, which ex- ploit the linguistic syntax of source lan- guage, usually separate decoding into two steps: parsing and translation. Although this separation makes tree-based decoding simple and …...

Machine translation benefits from two types of decoding techniques: consensus decoding over multiple hypotheses under a single model and system combination over hypotheses from different models. We present model combina- …...

We present the MT-NCD and MT-mNCD machine translation evaluation metrics as submission to the machine transla- tion evaluation shared task (MetricsMATR 2010). The metrics are based on nor- malized compression …...

The problem of language model adaptation in statistical machine translation is consid- ered. A mixture of language models is employed, which is obtained by clustering the bilingual training data. Unsupervised …...

This paper describes how to cluster to- gether the phrases of a phrase-based sta- tistical machine translation (SMT) sys- tem, using information in the phrase table itself. The clustering is …...

In modern machine translation practice, a sta- tistical phrasal or hierarchical translation sys- tem usually relies on a huge set of trans- lation rules extracted from bi-lingual train- ing data. …...

We present a novel scheme to apply fac- tored phrase-based SMT to a language pair with very disparate morphological struc- tures. Our approach relies on syntac- tic analysis on the …...

Translation systems are generally trained to optimize BLEU, but many alternative metrics are available. We explore how optimizing toward various automatic evaluation metrics (BLEU, METEOR, NIST, TER) affects the re- …...

This paper describes the Cambridge Uni- versity Engineering Department submis- sion to the Fifth Workshop on Statistical Machine Translation. We report results for the French-English and Spanish-English shared translation tasks …...

Several attempts have been made to learn phrase translation probabilities for phrase- based statistical machine translation that go beyond pure counting of phrases in word-aligned training data. Most approaches report …...

AbstractOne problem in statistical machine translation (SMT) is that the output often is ungrammatical. To address this issue, we have investigated the use of a grammar checker for two purposes …...

AbstractThis paper proposes to introduce a novel reordering model in the open-source Moses toolkit. The main idea is to provide weighted reordering hypotheses to the SMT decoder. These hypotheses are …...

We present a novel machine translation model which models translation by a linear sequence of operations. In contrast to the “N-gram” model, this sequence includes not only trans- lation but …...

Dependency structure, as a first step towards semantics, is believed to be helpful to improve translation quality. However, previous works on dependency structure based models typi- cally resort to insertion …...

Automated grammar correction techniques have seen improvement over the years, but there is still much room for increased perfor- mance. Current correction techniques mainly focus on identifying and correcting a …...

Many machine translation evaluation met- rics have been proposed after the seminal BLEU metric, and many among them have been found to consistently outperform BLEU, demonstrated by their better correlations …...

Tree-to-string translation is syntax-aware and efficient but sensitive to parsing errors. Forest- to-string translation approaches mitigate the risk of propagating parser errors into transla- tion errors by considering a forest …...

This paper describes the system presented for the English-Spanish translation task by the collaboration between CEU-UCH and UPV for 2011 WMT. A comparison of indepen- dent phrase-based translation models interpo- …...

This paper describes the JHU system combi- nation scheme used in WMT-11. The JHU system combination is based on confusion network alignment, and inherited the frame- work developed by (Karakos …...

Although discriminative training guarantees to improve statistical machine translation by in- corporating a large amount of overlapping fea- tures, it is hard to scale up to large data due to …...

Paraphrases are useful for statistical machine translation (SMT) and natural language pro- cessing tasks. Distributional paraphrase gen- eration is independent of parallel texts and syntactic parses, and hence is suitable …...

We present an empirical study of instance se- lection techniques for machine translation. In an active learning setting, instance selection minimizes the human effort by identifying the most informative sentences …...

While it is generally accepted that many trans- lation phenomena are correlated with linguis- tic structures, employing linguistic syntax for translation has proven a highly non-trivial task. The key assumption …...

We propose a novel technique of learning how to transform the source parse trees to improve the trans- lation qualities of syntax-based translation mod- els using synchronous context-free grammars. We …...

This paper describes the development op- erated into MANY for the 2011 WMT system combination evaluation campaign. Hypotheses from French/English and En- glish/French MT systems were combined with a new …...

We introduce a novel semi-automated metric, MEANT, that assesses translation utility by match- ing semantic role fillers, producing scores that cor- relate with human judgment as well as HTER but …...

This paper describes Meteor 1.3, our submis- sion to the 2011 EMNLP Workshop on Sta- tistical Machine Translation automatic evalua- tion metric tasks. New metric features include improved text normalization, …...

This paper presents the system we developed for the 2011 WMT Haitian Creole–English SMS featured translation task. Applying stan- dard statistical machine translation methods to noisy real-world SMS data in …...

Automatic evaluation metrics are fundamen- tally important for Machine Translation, al- lowing comparison of systems performance and efficient training. Current evaluation met- rics fall into two classes: heuristic approaches, like …...

Long-distance reordering remains one of the biggest challenges facing machine translation. We derive soft constraints from the source de- pendency parsing to directly address the re- ordering problem for the …...

RWTH participated in the System Combi- nation task of the Sixth Workshop on Sta- tistical Machine Translation (WMT 2011). For three language pairs, we combined 6 to 14 systems into …...

This paper describes the UZH system that was used for the WMT 2011 system combination shared task submission. We participated in the system combination task for the translation directions DE–EN …...

We describe TINE, a new automatic evalua- tion metric for Machine Translation that aims at assessing segment-level adequacy. Lexical similarity and shallow-semantics are used as indicators of adequacy between machine …...

Statistical post-editing (SPE) of the output produced by rule-based MT (RBMT) systems has been reported to produce extraordinary BLEU (and other automatic evaluation) score improvements. SPE has also been applied …...

AbstractThis paper describes the development of a statistical machine translation system between French and English for scientific papers. This system will be closely integrated into the French HAL open archive, …...

This paper proposes cross-lingual language modeling for transcribing source resource- poor languages and translating them into tar- get resource-rich languages if necessary. Our focus is to improve the speech recognition …...

We compare three methods of modeling morphological features in statistical ma- chine translation (SMT) from English to Arabic, a morphologically rich language. Features can be modeled as part of the …...

This paper presents a range of preprocess- ing solutions for Hebrew-English statisti- cal machine translation. Our best system, using a morphological analyzer, increases 3.5 BLEU points over a no-tokenization baseline …...

We present a sub-sentential alignment al- gorithm that relies on association scores between words or phrases. This algorithm is inspired by previous work on alignment by recursive binary segmentation and …...

This paper implements and compares three different strategies to use English as pivot language for Chinese-Japanese patent translation: corpus enrichment, sentence pivot translation and phrase pivot translation. Our results show …...

AbstractSignificant breakthroughs in machine translation only seem possible if human translators are taken into the loop. While automatic evaluation and scoring mechanisms such as BLEU have enabled the fast development …...

This paper describes LIMSI’s submissions to the shared translation task. We report results for French-English and German-English in both directions. Our submissions use n-code, an open source system based on …...

In statistical machine translation, minimum error rate training (MERT) is a standard method for tuning a single weight with regard to a given development data. However, due to the diversity …...

Comprehension and corpus studies have found that the tendency to minimize dependency length has a strong influence on constituent or- dering choices. In this paper, we investigate dependency length minimization …...

Tense is a small element to a sentence, how- ever, error tense can raise odd grammars and result in misunderstanding. Recently, tense has drawn attention in many natural language processing …...

We present an online learning algorithm for statistical machine translation (SMT) based on stochastic gradient descent (SGD). Under the online setting of rank learning, a corpus-wise loss has to be …...

This paper presents a novel approach to pivot-based machine translation (MT): while the state-of-the-art uses two statisti- cal systems, this proposal treats the second system as a black box. Our …...

We describe the systems developed by the team of the Qatar Computing Research Insti- tute for the WMT12 Shared Translation Task. We used a phrase-based statistical machine translation model with …...

Confusion network decoding has proven to be one of the most successful approaches to machine translation system combination. The hypothesis alignment algorithm is a cru- cial part of building the …...

In this paper, we propose a novel semantic cohesion model. Our model utilizes the predicate- argument structures as soft constraints and plays the role as a reordering model in the …...

We describe the systems submitted by SRI In- ternational and the University of the Basque Country for the Semantic Textual Similarity (STS) SemEval-2012 task. Our systems fo- cused on using …...

This paper describes the UPC participation in the WMT 12 evaluation campaign. All sys- tems presented are based on standard phrase- based Moses systems. Variations adopted sev- eral improvement techniques …...

We present a global log-linear model for synchronous grammar induction, which is capable of incorporating arbitrary features. The parameters in the model are trained in an unsuper- vised fashion from …...

This paper describes the UPM system for the Spanish-English translation task at the NAACL 2012 workshop on statistical ma- chine translation. This system is based on Mo- ses. We have …...

Most modern machine translation systems use phrase pairs as translation units, al- lowing for accurate modelling of phrase- internal translation and reordering. How- ever phrase-based approaches are much less able …...

In this paper, we propose a novel re- ordering model based on sequence label- ing techniques. Our model converts the reordering problem into a sequence label- ing problem, i.e. a …...

This paper provides an analysis of character-level machine translation mod- els used in pivot-based translation when applied to sparse and noisy datasets, such as crowdsourced movie subtitles. In our experiments, …...

In Statistical Machine Translation we often have to combine different sources of parallel training data to build a good system. One way of doing this is to build separate translation …...

We introduce bilingual word embeddings: se- mantic embeddings associated across two lan- guages in the context of neural language mod- els. We propose a method to learn bilingual embeddings from …...

We introduce dependency relations into deci- phering foreign languages and show that de- pendency relations help improve the state-of- the-art deciphering accuracy by over 500%. We learn a translation lexicon …...

Parallel text is the fuel that drives modern machine translation systems. The Web is a comprehensive source of preexisting par- allel text, but crawling the entire web is impossible for …...

Our field has seen significant improve- ments in the quality of machine translation systems over the past several years. The single biggest factor in this improvement has been the accumulation …...

AbstractDefining the reordering search space is a crucial issue in phrase-based SMT between distant languages. In fact, the optimal trade-off between accuracy and complexity of decoding is nowadays reached by …...

This paper aims at effective use of training da- ta by extracting sentences from large general- domain corpora to adapt statistical machine translation systems to domain-specific data. We regard this …...

There have been many recent investigations into methods to tune SMT systems using large numbers of sparse features. However, there have not been nearly so many examples of helpful sparse …...

Automatically clustering words from a mono- lingual or bilingual training corpus into classes is a widely used technique in statisti- cal natural language processing. We present a very simple and …...

We present a new variant of the Syntax- Augmented Machine Translation (SAMT) for- malism with a category-coarsening algorithm originally developed for tree-to-tree gram- mars. We induce bilingual labels into the …...

Since statistical machine translation (SMT) and translation memory (TM) complement each other in matched and unmatched regions, integrated models are proposed in this paper to incorporate TM information into phrase-based …...

We present a joint language and transla- tion model based on a recurrent neural net- work which predicts target words based on an unbounded history of both source and tar- …...

This paper describes the joint submis- sion of the QUAERO project for the German→English translation task of the ACL 2013 Eighth Workshop on Statisti- cal Machine Translation (WMT 2013). The …...

We present an iterative technique to gener- ate phrase tables for SMT, which is based on force-aligning the training data with a modified translation decoder. Differ- ent from previous work, …...

Lexical chains provide a representation of the lexical cohesion structure of a text. In this pa- per, we propose two lexical chain based co- hesion models to incorporate lexical cohesion …...

Traditional synchronous grammar induction estimates parameters by maximizing likeli- hood, which only has a loose relation to trans- lation quality. Alternatively, we propose a max-margin estimation approach to discrim- inatively …...

While large-scale discriminative training has triumphed in many NLP problems, its defi- nite success on machine translation has been largely elusive. Most recent efforts along this line are not scalable …...

N-gram-based models co-exist with their phrase-based counterparts as an alternative SMT framework. Both techniques have pros and cons. While the N-gram-based frame- work provides a better model that captures both …...

This paper examines tuning for statistical ma- chine translation (SMT) with respect to mul- tiple evaluation metrics. We propose several novel methods for tuning towards multiple ob- jectives, including some …...

Multi-task learning has been shown to be effective in various applications, including discriminative SMT. We present an exper- imental evaluation of the question whether multi-task learning depends on a “natu- …...

Research on statistical machine transla- tion has focused on particular translation directions, typically with English as the target language, e.g., from Arabic to En- glish. When we reverse the translation …...

This paper proposes a nonparametric Bayesian method for inducing Part-of- Speech (POS) tags in dependency trees to improve the performance of statistical machine translation (SMT). In particular, we extend the …...

We present Positive Diversity Tuning, a new method for tuning machine translation models specifically for improved perfor- mance during system combination. Sys- tem combination gains are often limited by the …...

This paper is to introduce our participation in the WMT13 shared tasks on Quality Estima- tion for machine translation without using ref- erence translations. We submitted the results for Task …...

While inversion transduction grammar (ITG) is well suited for modeling ordering shifts between languages, how to make applying the two reordering rules (i.e., straight and inverted) dependent on actual blocks …...

In this paper, we propose a new Bayesian inference method to train statistical ma- chine translation systems using only non- parallel corpora. Following a probabilis- tic decipherment approach, we first …...

We present a simple and novel classifier-based preordering approach. Unlike existing pre- ordering models, we train feature-rich dis- criminative classifiers that directly predict the target-side word order. Our approach com- …...

Arabic is a morphologically rich and complex language, which presents signifi- cant challenges for natural language pro- cessing and machine translation. In this paper, we describe an ongoing effort to …...

AbstractIn this paper, we propose two extensions to the vector space model (VSM) adaptation technique (Chen et al., 2013b) for statistical machine translation (SMT), both of which result in significant …...

We present a human judgments dataset and an adapted metric for evaluation of Arabic machine translation. Our medium- scale dataset is the first of its kind for Ara- bic with …...

Lexicalized reordering model plays a central role in phrase-based statistical machine translation sys- tems. The reordering model specifies the orientation for each phrase and calculates its probability con- ditioned on …...

BLEU is the de facto standard machine translation (MT) evaluation metric. How- ever, because BLEU computes a geo- metric mean of n-gram precisions, it of- ten correlates poorly with human …...

An important step in mainstream statisti- cal machine translation (SMT) is combin- ing bidirectional alignments into one align- ment model. This process is called sym- metrization. Most of the symmetrization …...

During decoding, the Statistical Machine Translation (SMT) decoder travels over all complete paths on the Search Graph (SG), seeks those with cheapest costs and back- tracks to read off the …...

As described in this paper, we pro- pose a new automatic evaluation met- ric for machine translation. Our met- ric is based on chunking between the reference and candidate translation. …...

In phrase-based statistical machine trans- lation systems, variation in grammatical structures between source and target lan- guages can cause large movements of phrases. Modeling such movements is cru- cial in …...

AbstractRecent years have seen increased interest in adapting translation models to test domains that are known in advance as well as using latent topic representations to adapt to unknown test …...

Scrambling is acceptable reordering of verb arguments in languages such as Japanese and German. In automatic eval- uation of translation quality, BLEU is the de facto standard method, but BLEU …...

This paper presents a novel approach to improve reordering in phrase-based ma- chine translation by using richer, syntac- tic representations of units of bilingual language models (BiLMs). Our method to …...

AbstractWe introduce two document-level features to polish baseline sentence-level translations generated by a state-of-the-art statistical machine translation (SMT) system. One feature uses the word-embedding technique to model the relation between …...

In this paper we explicitly consider source language syntactic information in both rule extraction and decoding for hierarchical phrase-based translation. We obtain tree-to-string rules by the GHKM method and use …...

AbstractThe training data size is of utmost importance for statistical machine translation (SMT), since it affects the training time, model size, decoding speed, as well as the system’s overall success. …...

Phrase-based translation models usually memorize local translation literally and make independent assumption between phrases which makes it neither generalize well on unseen data nor model sentence- level effects between phrases. …...

Statistical phrase-based translation learns translation rules from bilingual corpora, and has traditionally only used monolin- gual evidence to construct features that rescore existing translation candidates. In this work, we present …...

AbstractThis paper presents a Japanese-to-English statistical machine translation system specialized for patent translation. Patents are practically useful technical documents, but their translation needs different efforts from general-purpose translation. There are …...

We present power low rank ensembles (PLRE), a flexible framework for n-gram language modeling where ensembles of low rank matrices and tensors are used to obtain smoothed probability estimates of …...

This paper describes the LAYERED met- ric which is used for the shared WMT’14 metrics task. Various metrics exist for MT evaluation: BLEU (Papineni, 2002), ME- TEOR (Alon Lavie, 2007), …...

This paper describes Meteor Universal, re- leased for the 2014 ACL Workshop on Statistical Machine Translation. Meteor Universal brings language specific evalu- ation to previously unsupported target lan- guages by …...

Paraphrase evaluation is typically done ei- ther manually or through indirect, task- based evaluation. We introduce an in- trinsic evaluation PARADIGM which mea- sures the goodness of paraphrase col- lections …...

Topic models, an unsupervised technique for inferring translation domains improve machine translation quality. However, pre- vious work uses only the source language and completely ignores the target language, which can …...

Most of the widely-used automatic evaluation metrics consider only the local fragments of the references and translations, and they ignore the evaluation on the syntax level. Current syntax- based evaluation …...

Languages that have no explicit word de- limiters often have to be segmented for sta- tistical machine translation (SMT). This is commonly performed by automated seg- menters trained on manually …...

Parameter tuning is an important problem in statistical machine translation, but surpris- ingly, most existing methods such as MERT, MIRA and PRO are agnostic about search, while search errors could …...

We present a simple preordering approach for machine translation based on a feature- rich logistic regression model to predict whether two children of the same node in the source-side parse …...

We describe Stanford’s participation in the French-English and English-German tracks of the 2014 Workshop on Statisti- cal Machine Translation (WMT). Our sys- tems used large feature sets, word classes, and …...

We study a novel architecture for syntactic SMT. In contrast to the dominant approach in the literature, the system does not rely on translation rules, but treat translation as an …...

We present a novel approach to im- prove word alignment for statistical ma- chine translation (SMT). Conventional word alignment methods allow discontin- uous alignment, meaning that a source (or target) …...

AbstractAnalysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. …...

This work presents two different trans- lation models using recurrent neural net- works. The first one is a word-based ap- proach using word alignments. Second, we present phrase-based translation mod- …...

We describe an approach to word ordering using modelling techniques from statisti- cal machine translation. The system in- corporates a phrase-based model of string generation that aims to take unordered …...

We propose a conversion of bilingual sentence pairs and the corresponding word alignments into novel linear se- quences. These are joint translation and reordering (JTR) uniquely defined sequences, combining interdepending …...

Lexical sparsity is a major challenge for machine translation into morphologically rich lan- guages. We address this problem by modeling sequences of fine-grained morphological tags in a bilingual context. To …...

Learning semantic representations and tree structures of bilingual phrases is ben- eficial for statistical machine translation. In this paper, we propose a new neu- ral network model called Bilingual Corre- …...

This paper describes a novel target-side syntactic language model for phrase-based statistical machine translation, bilingual structured language model. Our approach represents a new way to adapt structured language models (Chelba …...

In English-to-Japanese translation, BLEU (Papineni et al., 2002), the de facto standard evaluation metric for machine translation (MT), has very weak corre- lation with human judgments (Goto et al., 2011; …...

In this paper the author presents meth- ods for dynamic terminology integration in statistical machine translation systems using a source text pre-processing work- flow. The workflow consists of exchange- able …...

An attentional mechanism has lately been used to improve neural machine transla- tion (NMT) by selectively focusing on parts of the source sentence during trans- lation. However, there has been …...

Word segmentation is helpful in Chinese nat- ural language processing in many aspects. However it is showed that different word seg- mentation strategies do not affect the per- formance of …...

We propose a novel extended translation model (ETM) to counteract some prob- lems in phrase-based translation: The lack of translation context when using single- word phrases and uncaptured dependen- cies …...

The multilingual Paraphrase Database (PPDB) is a freely available automatically created resource of paraphrases in mul- tiple languages. In statistical machine translation, paraphrases can be used to provide translation for …...

Translation models often fail to generate good translations for infrequent words or phrases. Previous work attacked this problem by in- ducing new translation rules from monolin- gual data with a …...

This paper describes the LeBLEU evalu- ation score for machine translation, sub- mitted to WMT15 Metrics Shared Task. LeBLEU extends the popular BLEU score to consider fuzzy matches between word …...

The log-linear combination of different features is an important component of SMT systems. It allows for the easy in- tegartion of models into the system and is used during decoding …...

The lack of parallel data for many language pairs is an important challenge to statistical ma- chine translation (SMT). One common solution is to pivot through a third language for …...

This paper addresses the problem of mor- phological modeling in statistical speech-to- speech translation for English to Iraqi Ara- bic. An analysis of user data from a real-time MT-based dialog …...

In this paper, we describe our submis- sion to WMT 2015 Tuning Task. We integrate a dependency-based MT evalu- ation metric, RED, to Moses and com- pare it with BLEU …...

We propose a method for simultaneously translating from a single source language to multiple target languages T1, T2, etc. The mo- tivation behind this method is that if we only …...

We provide an analysis of current evalua- tion methodologies applied to summariza- tion metrics and identify the following ar- eas of concern: (1) movement away from evaluation by correlation with …...

This paper presents the results of the WMT15 Tuning Shared Task. We pro- vided the participants of this task with a complete machine translation system and asked them to tune …...

Parameter tuning is a key problem for sta- tistical machine translation (SMT). Most popular parameter tuning algorithms for SMT are agnostic of decoding, result- ing in parameters vulnerable to search …...

This paper presents a machine transla- tion tool – based on Moses – developed for the International Maritime Organiza- tion (IMO) for the automatic translation of documents from Spanish, French, …...

This paper presented the joined submis- sion of KIT and LIMSI to the English to German translation task of WMT 2015. In this year submission, we integrated a neu- ral …...

This paper describes the statistical machine translation system developed at RWTH Aachen University for the German→English translation task of the EMNLP 2015 Tenth Workshop on Statistical Machine Translation (WMT 2015). …...

We introduce pre-post-editing, possibly the most basic form of interactive trans- lation, as a touch-based interaction with iteratively improved translation hypothe- ses prior to classical post-editing. We re- port simulated …...

Recent work in neural machine translation has shown promising performance, but the most effective architectures do not scale naturally to large vocabulary sizes. We propose and compare three variable-length encoding …...

Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., I don’t know) regardless of the input. We sug- gest that the traditional objective …...

Training discriminative rule selection models is usually expensive because of the very large size of the hierarchical gram- mar. Previous approaches reduced the training costs either by (i) using mod- …...

Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In re- sponse to …...

We present persona-based models for han- dling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed em- beddings that capture individual charac- teristics …...

Automatic Machine Translation metrics, such as BLEU, are widely used in empirical eval- uation as a substitute for human assessment. Subsequently, the performance of a given met- ric is measured …...

AbstractIn this paper, we present the KIT systems of the IWSLT 2016 machine translation evaluation. We participated in the machine translation (MT) task as well as the spoken language language …...

AbstractIn this paper, we propose a new data selection method which uses semi-supervised convolutional neural networks based on bitokens (Bi-SSCNNs) for training machine translation systems from a large bilingual corpus. …...

AbstractNeural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are …...

Poorly translated text is often disfluent and difficult to read. In contrast, well-formed translations require less time to process. In this paper, we model the differences in reading patterns of …...

AbstractIn this paper we investigate the potential of the neural machine translation (NMT) when taking into consideration the linguistic aspect of target language. From this standpoint, the NMT approach with …...

AbstractIn this paper, we describe FBK’s neural machine translation (NMT) systems submitted at the International Workshop on Spoken Language Translation (IWSLT) 2016. The systems are based on the state-of-the-art NMT …...

AbstractNatural language generation (NLG) is the task of generating natural language from a meaning representation. Current rule-based approaches require domain-specific and manually constructed linguistic resources, while most machine-learning based approaches …...

Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only us- ing parallel data for training. Target- side monolingual data plays an impor- tant role …...

Neural machine translation (NMT) often makes mistakes in translating low-frequency content words that are essential to understand- ing the meaning of the sentence. We propose a method to alleviate this …...

This paper presents an study of the use of in- terlocking phrases in phrase-based statistical machine translation. We examine the effect on translation quality when the translation units used in …...

We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but power- ful extension to the state in the decoding RNN. …...

Neural machine translation (NMT) mod- els typically operate with a fixed vocabu- lary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off …...

AbstractIn this paper, we propose a novel neural approach for paraphrase generation. Conventional paraphrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To …...

AbstractRecently, the development of neural machine translation (NMT) has significantly improved the translation quality of automatic machine translation. While most sentences are more accurate and fluent than translations by statistical …...

AbstractThis paper describes QCRI’s machine translation systems for the IWSLT 2016 evaluation campaign. We participated in the Arabic→English and English→Arabic tracks. We built both Phrase-based and Neural machine translation models, …...

Active learning is a framework that makes it possible to efficiently train statistical models by selecting informative examples from a pool of unlabeled data. Previous work has found this framework …...

AbstractThis paper describes a hybrid machine translation system that explores a parser to acquire syntactic chunks of a source sentence, translates the chunks with multiple online machine translation (MT) system …...

AbstractIn this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach in which the information shared among languages can be helpful …...

Neural network language and translation models have recently shown their great po- tentials in improving the performance of phrase-based machine translation. At the same time, word representations using dif- ferent …...

AbstractTraditional machine translation systems often require heavy feature engineering and the combination of multiple techniques for solving different subproblems. In recent years, several end-to-end learning architectures based on recurrent neural …...

Recent work on word ordering has argued that syntactic structure is important, or even re- quired, for effectively recovering the order of a sentence. We find that, in fact, an …...

Current machine translation systems require large bilingual corpora for training data. With large bilingual corpora, phrase-based and neural-based methods can achieve state-of-the-art performance. Nevertheless, such large bilingual corpora are unavailable …...

AbstractWhile end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose …...

AbstractTasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The …...

This paper describes the neural machine translation systems of the University of Latvia, University of Zurich and Univer- sity of Tartu. We participated in the WMT 2017 shared task on …...

AbstractWe present CHARCUT, a character-based machine translation evaluation metric derived from a human-targeted segment difference visualisation algorithm. It combines an iterative search for longest common substrings between the candidate and …...

AbstractThe goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted …...

AbstractDeep Neural Networks (DNNs) have provably enhanced the state-of-the-art Neural Machine Translation (NMT) with its capability in modeling complex functions and capturing complex linguistic structures. However NMT with deep architecture …...

AbstractIntelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of …...

Neural Machine Translation (NMT) models are often trained on hetero- geneous mixtures of domains, from news to parliamentary proceedings, each with unique distributions and lan- guage. In this work we …...

Linguistic resources such as part-of- speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded bet- ter performances. However, usage of such linguistic annotations …...

We describe a data selection method for domain adaptation in machine translation, based on relative frequency ratios computed between in-domain and out-of-domain corpora. Our method is compared to a state-of-the-art …...

In this paper we report on FBK’s par- ticipation to the English-to-German news translation task of the Second Conference on Machine Translation (WMT’17). The submitted system is based on Neural …...

AbstractRecent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zero-shot) translation directions not observed at training time. We …...

This paper describes LIUM submis- sions to WMT17 News Translation Task for English↔German, English↔Turkish, English→Czech and English→Latvian language pairs. We train BPE-based at- tentive Neural Machine Translation sys- tems with …...

This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. We mainly explored two mul- timodal architectures …...

AbstractSequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text using Abstract Meaning Representation (AMR) has been limited, due to …...

AbstractIn this paper, we introduce a hybrid search for attention-based neural machine translation (NMT). A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search …...

Hybrid machine translation (HMT) takes advantage of different types of machine translation (MT) systems to improve translation performance. Neural machine translation (NMT) can produce more fluent translations while phrase-based statistical …...

Neural machine translation (NMT) mod- els are able to partially learn syntactic in- formation from sequential lexical informa- tion. Still, some complex syntactic phe- nomena such as prepositional phrase at- …...

AbstractBy addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua. We strengthen the interlingual aspect of AMR by applying the multilingual Grammatical …...

AbstractWe explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific …...

AbstractAttentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. …...

AbstractThis paper describes an empirical study of the phrase-based decoding algorithm proposed by Chang and Collins (2017). The algorithm produces a translation by processing the source-language sentence in strictly left-to-right …...

For efficiency considerations, state-of-the- art neural machine translation (NMT) re- quires the vocabulary to be restricted to a limited-size set of several thousand sym- bols. This is highly problematic when …...

This paper describes the joint submis- sion of the QT21 projects for the English→Latvian translation task of the EMNLP 2017 Second Conference on Ma- chine Translation (WMT 2017). The sub- …...

AbstractAutomatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response …...

AbstractThe study on human-computer conversation systems is a hot research topic nowadays. One of the prevailing methods to build the system is using the generative Sequence-to-Sequence (Seq2Seq) model through neural …...

AbstractThis work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a …...

AbstractThe field of machine translation faces an under-recognized problem because of inconsistency in the reporting of scores from its dominant metric. Although people refer to “the” BLEU score, BLEU is …...

We present a dataset and method for improving the translation of noisy image captions that were created by users of Wikimedia Commons. The dataset is multilingual but non-parallel, and is …...

AbstractThe translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access …...

AbstractWe present an approach to interactivepredictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we …...

AbstractMultilingual neural machine translation (M-NMT) has recently shown to improve performance of machine translation of low-resource languages. Thanks to its implicit transfer-learning mechanism, the availability of a highly resourced language …...

BLEU is the most well-known automatic evaluation technology in assessing the performance of machine translation systems. However, BLEU does not know which parts of the NMT translation results are good …...

AbstractWe present a video captioning approach that encodes features by progressively completing syntactic structure (LSTM-CSS). To construct basic syntactic structure (i.e., subject, predicate, and object), we use a Conditional Random …...

AbstractThere has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam. In this paper, we survey a …...

AbstractRecent works in neural machine translation have begun to explore document translation. However, translating online multi-speaker conversations is still an open problem. In this work, we propose the task of …...

AbstractData selection techniques applied to neural machine translation (NMT) aim to increase the performance of a model by retrieving a subset of sentences for use as training data. One of …...

AbstractThe end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new …...

AbstractThis paper describes FBK’s submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs, where the CNNs …...

AbstractOne of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and effective …...

AbstractThis paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. …...

AbstractQuestion answering (QA) and question generation (QG) are closely related tasks that could improve each other; however, the connection of these two tasks is not well explored in literature. In …...

In this paper, we assess the challenges for multi-domain, multi-lingual question answering, create necessary resources for benchmarking and develop a baseline model. We curate 500 articles in six different domains …...

AbstractNeural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level …...

AbstractNeural machine translation with source-side attention have achieved remarkable performance. however, there has been little work exploring to attend to the target-side which can potentially enhance the memory capbility of …...

AbstractThis work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture. We demonstrate that alignment extraction in transformer models can be improved by augmenting an …...

AbstractIn multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually …...

AbstractSequence to sequence learning models still require several days to reach state of the art performance on large benchmark datasets using a single machine. This paper shows that reduced precision …...

AbstractIn neural machine translation, an attention model is used to identify the aligned source words for a target word (target foresight word) in order to select translation context, but it …...

AbstractThis paper presents the University of Helsinki submissions to the Basque–English low-resource translation task. Our primary system is a standard bilingual Transformer system, trained on the available parallel data and …...

AbstractTo enrich vocabulary of low resource settings, we proposed a novel method which identify loanwords in monolingual corpora. More specifically, we first use cross-lingual word embeddings as the core feature …...

In this paper, we present results of employing multilingual and multi-way neural machine translation approaches for morphologically rich languages, such as Estonian and Russian. We experiment with different NMT architectures …...

AbstractIn this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share …...

AbstractTo improve the translation adequacy in neural machine translation (NMT), we propose a rewarding model with target word prediction using bilingual dictionaries inspired by the success of decoder constraints in …...

AbstractWhile machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) …...

AbstractGenerating high-quality paraphrases is a fundamental yet challenging natural language processing task. Despite the effectiveness of previous work based on generative models, there remain problems with exposure bias in recurrent …...

AbstractMulti-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads to the …...

AbstractIn this work, we train an Automatic Post-Editing (APE) model and use it to reveal biases in standard MT evaluation procedures. The goal of our APE model is to correct …...

AbstractWhile most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly …...

AbstractWe aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original …...

AbstractIn Neural Machine Translation (NMT) the usage of sub-words and characters as source and target units offers a simple and flexible solution for translation of rare and unseen words. However, …...

AbstractDespite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in …...

AbstractTransfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques …...

This paper proposes a novel multilin- gual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese– Russian pair for benchmarking. Al- though there are many solutions …...

AbstractPrevious work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create …...

AbstractThe overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised …...

AbstractUnderstanding contrastive opinions is a key component of argument generation. Central to an argument is the claim, a statement that is in dispute. Generating a counter-argument then requires generating a …...

AbstractEllipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. In this paper, we treat the resolution of ellipsis and co-reference in dialogue as a problem of generating omitted …...

AbstractAutomatically generating animation from natural language text finds application in a number of areas e.g. movie script writing, instructional videos, and public safety. However, translating natural language text into animation …...

AbstractIt is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction. …...

AbstractAutomatically constructed datasets for generating text from semi-structured data (tables), such as WikiBio, often contain reference texts that diverge from the information in the corresponding semi-structured data. We show that …...

AbstractFor automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then trans- late with machine translation (MT). A major cause of …...

AbstractAn important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one …...

AbstractTransformer-based neural machine translation (NMT) has recently achieved state-of-the-art performance on many machine translation tasks. However, recent work (Raganato and Tiedemann, 2018; Tang et al., 2018; Tran et al., 2018) …...

AbstractTranscripts of natural, multi-person meetings differ significantly from documents like news articles, which can make Natural Language Generation models for generating summaries unfocused. We develop an abstractive meeting summarizer from …...

AbstractTable-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the …...

AbstractMachine translation is highly sensitive to the size and quality of the training data, which has led to an increasing interest in collecting and filtering large parallel corpora. In this …...

AbstractMost machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target …...

AbstractIncremental domain adaptation, in which a system learns from the correct output for each input immediately after making its prediction for that input, can dramatically improve system performance for interactive …...

Memory-augmented neural networks (MANNs) have been shown to outper- form other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to …...

AbstractRecent end-to-end task oriented dialog systems use memory architectures to incorporate external knowledge in their dialogs. Current work makes simplifying assumptions about the structure of the knowledge base, such as …...

AbstractMachine translation of ancient languages faces a low-resource problem, caused by the limited amount of available textual source data and their translations. We present a multi-task modeling approach to translating …...

AbstractWe propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than …...

AbstractThis paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019 for the English→ Portuguese language pair. ON-TRAC Consortium is composed of researchers …...

This paper is devoted to developing a re- current neural network (RNN) solution for segmenting the unpunctuated transcripts generated by automatic speech recognition for simultaneous interpretation. RNNs are effective in …...

AbstractWe introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that …...

AbstractWe present a simple approach to improve direct speech-to-text translation (ST) when the source language is low-resource: we pre-train the model on a high-resource automatic speech recognition (ASR) task, and …...

AbstractAutomatic question generation (QG) is a useful yet challenging task in NLP. Recent neural network-based approaches represent the state-of-the-art in this task. In this work, we attempt to strengthen them …...

AbstractSemantic parsing considers the task of transducing natural language (NL) utterances into machine executable meaning representations (MRs). While neural network-based semantic parsers have achieved impressive improvements over previous methods, results …...

AbstractIt has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data …...

AbstractRegularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in …...

AbstractThis paper describes the submission to IWSLT 2019 End- to-End speech translation task by Samsung R&D Institute, Poland. We decided to focus on end-to-end English to German TED lectures translation …...

AbstractNeural architectures based on self-attention, such as Transformers, recently attracted interest from the research community, and obtained significant improvements over the state of the art in several tasks. We explore …...

AbstractWe present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way …...

AbstractEvaluating AMR parsing accuracy involves comparing pairs of AMR graphs. The major evaluation metric, SMATCH (Cai and Knight, 2013), searches for one-to-one mappings between the nodes of two AMRs with …...

AbstractFor evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming. The most common automatic metrics, like BLEU and ROUGE, …...

AbstractThis paper shows that standard assessment methodology for style transfer has several significant problems. First, the standard metrics for style accuracy and semantics preservation vary significantly on different re-runs. Therefore …...

AbstractExisting approaches to neural machine translation (NMT) generate the target language sequence token-by-token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the …...

AbstractSyntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN …...

AbstractAlthough Seq2Seq models for table-to-text generation have achieved remarkable progress, modeling table representation in one dimension is inadequate. This is because (1) the table consists of multiple rows and columns, …...

AbstractTo improve low-resource Neural Machine Translation (NMT) with multilingual corpus, training on the most related high-resource language only is generally more effective than us- ing all data available (Neubig and …...

AbstractWe evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PRENORM) and smaller initializations enable warmup-free, validation-based training with large learning rates. Second, …...

AbstractIn this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under …...

AbstractThe transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first …...

AbstractWe present the first dataset for tracking state changes in procedural text from arbitrary domains by using an unrestricted (open) vocabulary. For example, in a text describing fog removal using …...

AbstractMost current state-of-the art systems for generating English text from Abstract Meaning Representation (AMR) have been evaluated only using automated metrics, such as BLEU, which are known to be problematic …...

AbstractMulti-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention heads can be pruned without significant …...

AbstractWe present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where there is …...

AbstractTransliteration is generally a phonetically based transcription across different writing systems. It is a crucial task for various downstream natural language processing applications. For the Myanmar (Burmese) language, robust automatic …...

AbstractMost of the existing models for document-level machine translation adopt dual-encoder structures. The representation of the source sentences and the document-level contexts are modeled with two separate encoders. Although these …...

AbstractWe investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference. Using modern neural paraphrasing techniques, we study whether automatically generating additional *diverse* references …...

AbstractInformation in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we …...

AbstractThis paper proposes a simple and effective approach to address the problem of posterior collapse in conditional variational autoencoders (CVAEs). It thus improves performance of machine translation models that use …...

AbstractIn this paper, we propose a new adversarial augmentation method for Neural Machine Translation (NMT). The main idea is to minimize the vicinal risk over virtual sentences sampled from two …...

AbstractAbstract meaning representation (AMR)-to-text generation is the challenging task of generating natural language texts from AMR graphs, where nodes represent concepts and edges denote relations. The current state-of-the-art methods use …...

AbstractWe present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the …...

AbstractSign Language Translation (SLT) first uses a Sign Language Recognition (SLR) system to extract sign language glosses from videos. Then, a translation system generates spoken language translations from the sign …...

AbstractThis paper proposed a new subword segmentation method for neural machine translation, “Bilingual Subword Segmentation,” which tokenizes sentences to minimize the difference between the number of subword units in a …...

AbstractText generation has made significant advances in the last few years. Yet, evaluation metrics have lagged behind, as the most popular choices (e.g., BLEU and ROUGE) may correlate poorly with …...

AbstractSubword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent …...

Constrained decoding forces a certain set words or phrases to appear in the translation results and is very useful when adapting MT to a certain domain. In recent years, the …...

AbstractVirtual Assistants can be quite literal at times. If the user says “tell Bob I love him,” most virtual assistants will extract the message “I love him” and send it …...

AbstractIn this paper, we investigate a commonsense inference task that unifies natural language understanding and commonsense reasoning. We describe our attempt at SemEval-2020 Task 4 competition: Commonsense Validation and Explanation …...

AbstractThis paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian. We experimented with training …...

AbstractWe present in this report our submission to IWSLT 2020 Open Domain Translation Task. We built a data pre-processing pipeline to efficiently handle large noisy web-crawled corpora, which boosts the …...

AbstractBack-translation has proven to be an effective method to utilize monolingual data in neural machine translation (NMT), and iteratively conducting back-translation can further improve the model performance. Selecting which monolingual …...

AbstractThis article describes the systems submitted by Elhuyar to the 2020 Biomedical Translation Shared Task, specifically the systems presented in the subtasks of terminology translation for English-Basque and abstract translation …...

AbstractIn this paper, we describe the system submitted to the IWSLT 2020 Offline Speech Translation Task. We adopt the Transformer architecture coupled with the meta-learning approach to build our end-to-end …...

AbstractIn this paper, we describe end-to-end simultaneous speech-to-text and text-to-text translation systems submitted to IWSLT2020 online translation challenge. The systems are built by adding wait-k and meta-learning approaches to the …...

AbstractThis paper describes FBK’s participation in the IWSLT 2020 offline speech translation (ST) task. The task evaluates systems’ ability to translate English TED talks audio into German texts. The test …...

AbstractExisting automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via …...

AbstractWe present an extended study on using pretrained language models and YiSi-1 for machine translation evaluation. Although the recently proposed contextual embedding based metrics, YiSi-1, significantly outperform BLEU and other …...

AbstractThe deployment of widely used Transformer architecture is challenging because of heavy computation load and memory overhead during inference, especially when the target device is limited in computational resources such …...

AbstractNeural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose …...

AbstractWe present the results of the 6th round of the WMT task on MT Automatic Post-Editing. The task consists in automatically correcting the output of a “black-box” machine translation system …...

AbstractWe report the results of the first edition of the WMT shared task on chat translation. The task consisted of translating bilingual conversational text, in particular customer support chats for …...

AbstractSimultaneous speech-to-speech translation is an extremely challenging but widely useful scenario that aims to generate target-language speech only a few seconds behind the source-language speech. In addition, we have to …...

AbstractState-of-the-art neural machine translation methods employ massive amounts of parameters. Drastically reducing computational costs of such methods without affecting performance has been up to this point unsuccessful. To this end, …...

AbstractFor text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is …...

AbstractOne of the fundamental goals of artificial intelligence is to build computer-based expert systems. Inferring clinical diagnoses to generate a clinical assessment during a patient encounter is a crucial step …...

AbstractKnowledge-driven conversation approaches have achieved remarkable research attention recently. However, generating an informative response with multiple relevant knowledge without losing fluency and coherence is still one of the main challenges. …...

AbstractThis paper describes the Global Tone Communication Co., Ltd.’s submission of the WMT20 shared news translation task. We participate in four directions: English to (Khmer and Pashto) and (Khmer and …...

AbstractEfficient document summarization requires evaluation measures that can not only rank a set of systems based on an average score, but also highlight which individual summary is better than another. …...

AbstractAutomatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by freitag2020bleu. When used in place of original references, the paraphrased versions produce metric scores …...

AbstractQuite surprisingly, exact maximum a posteriori (MAP) decoding of neural language generators frequently leads to low-quality results. Rather, most state-of-the-art results on language generation tasks are attained using beam search …...

AbstractIn this study, linguistic knowledge at different levels are incorporated into the neural machine translation (NMT) framework to improve translation quality for language pairs with extremely limited data. Integrating manually …...

AbstractMassively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. …...

AbstractOpen-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on …...

AbstractWith the proliferation of models for natural language processing tasks, it is even harder to understand the differences between models and their relative merits. Simply looking at differences between holistic …...

AbstractThe Transformer translation model employs residual connection and layer normalization to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. Previous research shows that even with residual connection and …...

AbstractDespite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be …...

AbstractUnsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data. This paper investigates the scenario where monolingual data …...

AbstractPretrained masked language models (MLMs) require finetuning for most NLP tasks. Instead, we evaluate MLMs out of the box via their pseudo-log-likelihood scores (PLLs), which are computed by masking tokens …...

AbstractRecent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting …...

AbstractWe propose a novel adapter layer formalism for adapting multilingual models. They are more parameter-efficient than existing adapter layers while obtaining as good or better performance. The layers are specific …...

AbstractTransformer models achieve remarkable success in Neural Machine Translation. Many efforts have been devoted to deepening the Transformer by stacking several units (i.e., a combination of Multihead Attentions and FFN) …...

AbstractMultiword Expressions (MWEs) are a frequently occurring phenomenon found in all natural languages that is of great importance to linguistic theory, natural language processing applications, and machine translation systems. Neural …...

AbstractThis paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a …...

Recent studies on direct speech translation show continuous improvements by means of data augmentation techniques and bigger deep learning models. While these methods are helping to close the gap between …...

AbstractPre-trained Transformers have enabled impressive breakthroughs in generating long and fluent text, yet their outputs are often “rambling” without coherently arranged content. In this work, we present a novel content-controlled …...

AbstractWe describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system. We build on …...

AbstractThe language used by physicians and health professionals in prescription directions includes medical jargon and implicit directives and causes much confusion among patients. Human intervention to simplify the language at …...

AbstractEnd-to-end models for speech translation (ST) more tightly couple speech recognition (ASR) and machine translation (MT) than a traditional cascade of separate ASR and MT models, with simpler model architectures …...

AbstractThis paper describes POSTECH-ETRI’s submission to WMT2020 for the shared task on automatic post-editing (APE) for 2 language pairs: English-German (En-De) and English-Chinese (En-Zh). We propose APE systems based on …...

AbstractThis paper describes the PROMT submissions for the WMT 2020 Shared News Translation Task. This year we participated in four language pairs and six directions: English-Russian, Russian-English, English-German, German-English, Polish-English …...

AbstractSimultaneously modeling source code and natural language has many exciting applications in automated software development and understanding. Pursuant to achieving such technology, we introduce PyMT5, the Python method text-to-text transfer …...

AbstractLow-resource language translation is a challenging but socially valuable NLP task. Building on recent work adapting the Transformer’s normalization to this setting, we propose QKNorm, a normalization technique that modifies …...

AbstractTraining data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to …...

AbstractQuestion generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer. While sequence to sequence neural …...

AbstractUsing a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data …...

AbstractOne of the most challenging part of recipe generation is to deal with the complex restrictions among the input ingredients. Previous researches simplify the problem by treating the inputs independently …...

AbstractDespite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models …...

AbstractThis paper presents the first attempt at Automatic Text Simplification (ATS) for Urdu, the language of 170 million people worldwide. Being a low-resource language in terms of standard linguistic resources, …...

AbstractMany valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference …...

AbstractSimultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with …...

AbstractAdaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous …...

AbstractModels that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve OOD generalization. …...

AbstractThis paper proposed a supervised visual attention mechanism for multimodal neural machine translation (MNMT), trained with constraints based on manual alignments between words in a sentence and their corresponding regions …...

AbstractThis paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks. We participate in the shared news translation task on English ↔ Chinese and English → …...

AbstractThis report summarizes the Air Force Research Laboratory (AFRL) submission to the offline spoken language translation (SLT) task as part of the IWSLT 2020 evaluation campaign. As in previous years, …...

AbstractIn this paper, we reproduce some of the experiments related to neural network training for Machine Translation as reported in (Vanmassenhove and Way, 2018). They annotated a sample from the …...

AbstractThis paper describes the joint participation of University of Helsinki and Aalto University to two shared tasks of WMT 2020: the news translation between Inuktitut and English and the low-resource …...

AbstractThis paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation. We focus on translating agent-side utterances from English to German. We started from an …...

AbstractWe propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting. This approach relies on touch actions that users perform to indicate translation errors. …...

Although some linguists (Rusmali et al., 1985; Crouch, 2009) have fairly attempted to de- fine the morphology and syntax of Minangk- abau, information processing in this language is still absent …...

AbstractDespite the success of existing referenced metrics (e.g., BLEU and MoverScore), they correlate poorly with human judgments for open-ended text generation including story or dialog generation because of the notorious …...

AbstractIn this paper, we introduce University of Tsukuba’s submission to the IWSLT20 Open Domain Translation Task. We participate in both Chinese→Japanese and Japanese→Chinese directions. For both directions, our machine translation …...

AbstractNeural network methods exhibit strong performance only in a few resource-rich domains. Practitioners therefore employ domain adaptation from resource-rich domains that are, in most cases, distant from the target domain. …...

AbstractDespite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored by the NLP community. …...

AbstractSentence weighting is a simple and powerful domain adaptation technique. We carry out domain classification for computing sentence weights with 1) language model cross entropy difference 2) a convolutional neural …...

AbstractBERTScore, a recently proposed automatic metric for machine translation quality, uses BERT, a large pre-trained language model to evaluate candidate translations with respect to a gold translation. Taking advantage of …...

AbstractReproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing interest in …...

AbstractThe metrics standardly used to evaluate Natural Language Generation (NLG) models, such as BLEU or METEOR, fail to provide information on which linguistic factors impact performance. Focusing on Surface Realization …...

AbstractDocument-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive …...

AbstractTransformers have advanced the field of natural language processing (NLP) on a variety of important tasks. At the cornerstone of the Transformer architecture is the multi-head attention (MHA) mechanism which …...

AbstractAlthough many end-to-end context-aware neural machine translation models have been proposed to incorporate inter-sentential contexts in translation, these models can be trained only in domains where parallel documents with sentential …...

AbstractLexical disambiguation is a major challenge for machine translation systems, especially if some senses of a word are trained less often than others. Identifying patterns of overgeneralization requires evaluation methods …...

AbstractContext-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation. Many existing works on context-aware NMT have focused on …...

AbstractExisting multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an …...

AbstractDefinition modelling is the task of automatically generating a dictionary-style definition given a target word. In this paper, we consider cross-lingual definition generation. Specifically, we generate English definitions for Wolastoqey …...

AbstractPrevious studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not …...

AbstractHuman evaluation has always been expensive while researchers struggle to trust the automatic metrics. To address this, we propose to customise traditional metrics by taking advantages of the pre-trained language …...

AbstractIn this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely …...

AbstractIn this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT’21 Large Scale Multilingual Translation Task - Small Track 2. We submit a …...

AbstractThis paper describes FBK’s system submission to the IWSLT 2021 Offline Speech Translation task. We participated with a direct model, which is a Transformer-based architecture trained to translate English speech …...

AbstractSpoken language is different from the written language in its style and structure. Disfluencies that appear in transcriptions from speech recognition systems generally hamper the performance of downstream NLP tasks. …...

AbstractRecent advancements in data-to-text generation largely take on the form of neural end-to-end systems. Efforts have been dedicated to improving text generation systems by changing the order of training samples …...

AbstractDespite constant improvements in machine translation quality, automatic poetry translation remains a challenging problem due to the lack of open-sourced parallel poetic corpora, and to the intrinsic complexities involved in …...

AbstractThis paper describes Edinburgh’s submissions to the IWSLT2021 multilingual speech translation (ST) task. We aim at improving multilingual translation and zero-shot performance in the constrained setting (without using any extra …...

AbstractDocument grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update …...

AbstractThis paper describes Huawei Artificial Intelligence Application Research Center’s neural machine translation systems and submissions to the WMT21 biomedical translation shared task. Four of the submissions achieve state-of-the-art BLEU scores …...

AbstractThis paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use …...

AbstractThis paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC). Technical …...

In the past few years, generative adversarial networks (GANs) have become increasingly important in natural language generation. How- ever, their performance seems to still have a sig- nificant margin for …...

AbstractTable-to-text generation aims at automatically generating natural text to help people conveniently obtain salient information in tables. Although neural models for table-to-text have achieved remarkable progress, some problems are still …...

AbstractWe investigate transfer learning based on pre-trained neural machine translation models to translate between (low-resource) similar languages. This work is part of our contribution to the WMT 2021 Similar Languages …...

AbstractSimultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay. However, due to the …...

AbstractPretraining and multitask learning are widely used to improve the speech translation performance. In this study, we are interested in training a speech translation model along with an auxiliary text …...

AbstractSuccessful methods for unsupervised neural machine translation (UNMT) employ cross-lingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the …...

AbstractMultilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output …...

AbstractThe performance of natural language generation systems has improved substantially with modern neural networks. At test time they typically employ beam search to avoid locally optimal but globally suboptimal predictions. …...

AbstractFor most language combinations and parallel data is either scarce or simply unavailable. To address this and unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic …...

AbstractTraditional translation systems trained on written documents perform well for text-based translation but not as well for speech-based applications. We aim to adapt translation models to speech by introducing actual …...

AbstractInteractive-predictive translation is a collaborative iterative process and where human translators produce translations with the help of machine translation (MT) systems interactively. Various sampling techniques in active learning (AL) exist …...

Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models. However, ex- isting studies show that parallel TS corpora contain inaccurate simplifications …...

AbstractHow to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a …...

AbstractMultilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration …...

Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its …...

Fully non-autoregressive neural machine trans- lation (NAT) simultaneously predicts tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to …...

Text generation from semantic parses is to generate textual descriptions for formal rep- resentation inputs such as logic forms and SQL queries. This is challenging due to two reasons: (1) …...

AbstractBeam search is the go-to method for decoding auto-regressive machine translation models. While it yields consistent improvements in terms of BLEU, it is only concerned with finding outputs with high …...

AbstractBased on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT. To this end …...

AbstractNeural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performance of sentence-level and context-aware Neural Machine Translation …...

AbstractOne of the reasons Transformer translation models are popular is that self-attention networks for context modelling can be easily parallelized at sequence level. However, the computational complexity of a self-attention …...

AbstractIndia is known as the land of many tongues and dialects. Neural machine translation (NMT) is the current state-of-the-art approach for machine translation (MT) but performs better only with large …...

AbstractWe present a simple yet effective approach to build multilingual speech-to-text (ST) translation through efficient transfer learning from a pretrained speech encoder and text decoder. Our key finding is that …...

AbstractWe consider the problem of multilingual unsupervised machine translation, translating to and from languages that only have monolingual data by using auxiliary parallel language pairs. For this problem the standard …...

AbstractThis paper describes Netmarble’s submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair’s WMT19 …...

AbstractFor many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available …...

AbstractIn this paper and we explore different techniques of overcoming the challenges of low-resource in Neural Machine Translation (NMT) and specifically focusing on the case of English-Marathi NMT. NMT systems …...

AbstractThis paper describes Naver Papago’s submission to the WMT21 shared triangular MT task to enhance the non-English MT system with tri-language parallel data. The provided parallel data are Russian-Chinese (direct), …...

We release our synthetic parallel paraphrase corpus across 17 languages: Arabic, Catalan, Czech, German, English, Spanish, Estonian, French, Hindi, Indonesian, Italian, Dutch, Ro- manian, Russian, Swedish, Vietnamese, and Chinese. Our …...

AbstractThe Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation. Therefore, the NMT model naturally involves the mechanism of …...

AbstractDue to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic …...

AbstractRecent research questions the importance of the dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. In this paper, we push further in this …...

AbstractThis work introduces a simple regressive ensemble for evaluating machine translation quality based on a set of novel and established metrics. We evaluate the ensemble using a correlation to expert-based …...

This work studies the long-standing prob- lems of model capacity and negative interfer- ence in multilingual neural machine transla- tion (MNMT). We use network pruning tech- niques and observe that …...

AbstractMachine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an ‘open vocabulary.’ This approach relies on consistent and correct underlying unicode sequences, and makes models …...

AbstractThis paper presents the first large-scale meta-evaluation of machine translation (MT). We annotated MT evaluations conducted in 769 research papers published from 2010 to 2020. Our study shows that practices …...

AbstractIn this paper and we identify an interesting kind of error in the output of Unsupervised Neural Machine Translation (UNMT) systems like Undreamt1. We refer to this error type as …...

AbstractEnd-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, …...

AbstractIn supervised learning, a well-trained model should be able to recover ground truth accurately, i.e. the predicted labels are expected to resemble the ground truth labels as much as possible. …...

AbstractI participated in the WMT shared news translation task and focus on one high resource language pair: English and Chinese (two directions, Chinese to English and English to Chinese). The …...

AbstractThe paper describes the TenTrans’s submissions to the WMT 2021 Efficiency Shared Task. We explore training a variety of smaller compact transformer models using the teacher-student setup. Our model is …...

AbstractThis paper describes the submission of LMU Munich to the WMT 2021 multilingual machine translation task for small track #1, which studies translation between 6 languages (Croatian, Hungarian, Estonian, Serbian, …...

AbstractThis paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text directly without intermediate …...

AbstractThis paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French …...

AbstractThis paper describes the Volctrans’ submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation system using the Glancing Transformer, which enables …...

AbstractReliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve …...

AbstractPerformance prediction, the task of estimating a system’s performance without performing experiments, allows us to reduce the experimental burden caused by the combinatorial explosion of different datasets, languages, tasks, and …...

AbstractThis paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German–Lower Sorbian (DE–DSB): a high-resource language to …...