BLEU Score

The parameters of statistical translation models are typically estimated from sentence-aligned parallel corpora. We show that significant improvements in the alignment and translation quality of such mod- els can be …...

If two translation systems differ differ in perfor- mance on a test set, can we trust that this indicates a difference in true system quality? To answer this question, we …...

We describe a method for incorporating syntactic informa- tion in statistical machine translation systems. The first step of the method is to parse the source language string that is be- …...

. In statistical machine translation, word alignment models are trained on bilingual corpora. Long sentences pose severe problems: 1. the high computational requirements; 2. the poor quality of the resulting …...

We present a method for improving statistical machine translation perfor- mance by using linguistically motivated syntactic information. Our algo- rithm recursively decomposes source language sentences into syntactically simpler and shorter …...

AbstractContext-Based Machine TranslationTM (CBMT) is a new paradigm for corpus-based translation that requires no parallel text. Instead, CBMT relies on a lightweight translation model utilizing a fullform bilingual dictionary and …...

AbstractThis paper presents our study of exploiting morpho-syntactic information for phrase-based statistical machine translation (SMT). For morphological transformation, we use hand-crafted transformational rules. For syntactic transformation, we propose a transformational …...

We propose a novel reordering model for phrase-based statistical machine transla- tion (SMT) that uses a maximum entropy (MaxEnt) model to predicate reorderings of neighbor blocks (phrase pairs). The model …...

AbstractIn this paper, we present a novel approach to combine the outputs of multiple MT engines into a consensus translation. In contrast to previous Multi-Engine Machine Translation (MEMT) techniques, we …...

Word posterior probabilities are a com- mon approach for confidence estimation in automatic speech recognition and ma- chine translation. We will generalize this idea and introduce n-gram posterior prob- abilities …...

Statistical MT has made great progress in the last few years, but current translation models are weak on re-ordering and target language fluency. Syn- tactic approaches seek to remedy these …...

In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forest- to-string rule is capable of capturing non- syntactic phrase pairs by describing …...

The paper proposes formulating MT evalu- ation as a ranking problem, as is often done in the practice of assessment by human. Un- der the ranking scenario, the study also …...

One style of Multi-Engine Machine Translation architecture involves choos- ing the best of a set of outputs from different systems. Choosing the best translation from an arbitrary set, even in …...

We take a multi-pass approach to ma- chine translation decoding when using syn- chronous context-free grammars as the trans- lation model and n-gram language models: the first pass uses a …...

Part of the unique cultural heritage of China is the game of Chinese couplets (duìlián). One person challenges the oth- er person with a sentence (first sentence). The other person …...

We describe the experiments of the UC Berke- ley team on improving English-Spanish ma- chine translation of news text, as part of the WMT’08 Shared Translation Task. We ex- periment …...

Documents in languages such as Chinese, Japanese and Korean sometimes annotate terms with their translations in English inside a pair of parentheses. We present a method to extract such translations …...

This paper studies three techniques that improve the quality of N-best hypotheses through additional regeneration process. Unlike the multi-system consensus ap- proach where multiple translation sys- tems are used, our …...

The BLEU scores and translation fluency for the current state-of-the-art SMT systems based on IBM models are still too low for publication purposes. The major issue is that stochastically generated …...

This paper shows that discriminative reranking with an averaged perceptron model yields substantial improvements in realization quality with CCG. The paper confirms the utility of including language model log probabilities …...

We introduce a syntactically enhanced word alignment model that is more flex- ible than state-of-the-art generative word alignment models and can be tuned ac- cording to different end tasks. First …...

Recent research has shown that Phrase- Based Statistical Machine Translation (PB-SMT) systems can benefit from two enhancements: (i) using words and POS tags as context-informed features on the source side; …...

We present a simple, robust generation system which performs content selection and surface realization in a unified, domain-independent framework. In our approach, we break up the end-to-end generation process into …...

Example-Based Machine Translation (EBMT), like other corpus based methods, requires substantial parallel training data. One way to reduce data requirements and improve translation quality is to generalize parts of the …...

In Arabic-to-English phrase-based statis- tical machine translation, a large number of syntactic disfluencies are due to wrong long-range reordering of the verb in VSO sentences, where the verb is anticipated …...

The paper presents an exploratory study of the translation processes for 12 student and 12 professional translators. We re- late properties of the translators’ process data (eye movements and keystrokes) …...

While Inversion Transduction Grammar (ITG) has regained more and more attention in recent years, it still suffers from the major obstacle of speed. We propose a discriminative ITG prun- ing …...

Hierarchical phrase-based machine trans- lation can capture global reordering with synchronous context-free grammar, but has little ability to evaluate the correctness of word orderings during decoding. We propose a method …...

We present a novel approach to integrate transliteration into Hindi-to-Urdu statisti- cal machine translation. We propose two probabilistic models, based on conditional and joint probability formulations, that are novel solutions …...

Statistical machine translation relies heav- ily on parallel corpora to train its mod- els for translation tasks. While more and more bilingual corpora are readily avail- able, the quality of …...

In most statistical machine translation (SMT) systems, bilingual segments are ex- tracted via word alignment. However, there lacks systematic study as to what alignment characteristics can benefit MT under specific …...

This paper presents an attempt at building a large scale distributed composite language model that simultaneously accounts for local word lexical information, mid-range sentence syntactic structure, and long-span document semantic …...

We present a novel approach for extracting a minimal synchronous context-free grammar (SCFG) for Hiero-style statistical machine translation using a non-parametric Bayesian framework. Our approach is designed to ex- tract …...

Statistical machine translation systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring document-level information. In this paper, we propose …...

In the present paper, we propose the ef- fective usage of function words to generate generalized translation rules for forest-based translation. Given aligned forest-string pairs, we extract composed tree-to-string translation …...

The quality of Arabic-English statistical ma- chine translation often suffers as a result of standard phrase-based SMT systems’ inabil- ity to perform long-range re-orderings, specif- ically those needed to translate …...

One of the major challenges facing statistical machine translation is how to model differ- ences in word order between languages. Al- though a great deal of research has focussed on …...

Translation results suffer when a standard phrase-based statistical machine transla- tion system is used for translating long sen- tences. The translation output will not pre- serve the same word order …...

Machine-produced text often lacks grammat- icality and fluency. This paper studies gram- maticality improvement using a syntax-based algorithm based on CCG. The goal of the search problem is to find …...

In this paper, we address the issue of ap- plying example-based machine transla- tion (EBMT) methods to overcome some of the difficulties encountered with stat- istical machine translation (SMT) tech- …...

We describe two methods for syntactic source reordering developed for English-German SMT. Both methods learn from bilingual data accompanied by automatic word alignments to reorder the source such that it …...

AbstractWe present a method for improving word alignment quality for phrase-based statistical machine translation by reordering the source text according to the target word order suggested by an initial word …...

Statistical-based methods are the preva- lent approaches for implementing machine translation systems today. However the resulted translations are usually flawed to some degree. We assume that a statisti- cal baseline …...

We describe a substitution-based system for hybrid machine translation (MT) that has been extended with machine learning components controlling its phrase selection. The approach is based on a rule-based MT …...

AbstractWe propose a pre-processing stage for Statistical Machine Translation (SMT) systems where the words of the source sentence are re-ordered as per the syntax of the target language prior to …...

Current word alignment models for statisti- cal machine translation do not address mor- phology beyond merely splitting words. We present a two-level alignment model that dis- tinguishes between words and …...

Translating from English, a morphologi- cally poor language, into morphologically rich languages such as Persian comes with many challenges. In this paper, we present an approach to rich morphology predic- …...

Using Chinese characters as an intermedi- ate equivalent unit, we decompose machine translation into two stages, semantic transla- tion and grammar translation. This strategy is tentatively applied to machine translation …...

In this paper, we propose an augmented dependency-to-string model to combine the merits of both the head-dependents relations at handling long distance reordering and the fixed and floating structures at …...

We present a novel segmentation ap- proach for Phrase-Based Statistical Ma- chine Translation (PB-SMT) to languages where word boundaries are not obviously marked by using both monolingual and bi- lingual …...

AbstractIn this paper, we present a method of improving the accuracy of machine translation evaluation of Czech sentences. Given a reference sentence, our algorithm transforms it by targeted paraphrasing into …...

In this paper we improve Urdu→Hindi⇄English machine trans- lation through triangulation and translit- eration. First we built an Urdu→Hindi SMT system by inducing triangulated and transliterated phrase-tables from Urdu–English and …...

We cast multi-sentence compression as a structured prediction problem. Related sentences are represented by a word graph so that summaries constitute paths in the graph (Filippova, 2010). We devise a …...

In this paper, we propose a recurrent neural network-based tuple sequence model (RNNTSM) that can help phrase-based translation model overcome the phrasal independence assumption. Our RNNTSM can potentially capture arbitrary …...

This paper proposes a soft dependency matching model for hierarchical phrase-based (HPB) machine translation. When a HPB rule is extracted, we enrich it with dependency knowledge automatically learnt from the …...

We present a French to English transla- tion system for Wikipedia biography ar- ticles. We use training data from out- of-domain corpora and adapt the system for biographies. We propose …...

This paper describes the joined submis- sion of LIMSI and KIT to the Shared Translation Task for the German-to- English direction. The system consists of a phrase-based translation system us- …...

We propose a novel dependency-based re- ordering model for hierarchical SMT that predicts the translation order of two types of pairs of constituents of the source tree: head-dependent and dependent-dependent. …...

We present a multi-task learning approach that jointly trains three word alignment mod- els over disjoint bitexts of three languages: source, target and pivot. Our approach builds upon model triangulation, …...

This paper presents a method for cleaning and evaluating parallel corpora using word alignments and machine learning algorithms. It is based on the assumption that parallel sentences have many word …...

One of the major challenges for statisti- cal machine translation (SMT) is to choose the appropriate translation rules based on the sentence context. This paper pro- poses a continuous space …...

AbstractWe present a new Bayesian HMM word alignment model for statistical machine translation. The model is a mixture of an alignment model and a language model. The alignment component is …...

AbstractOpenSubtitles.org provides a large collection of user contributed subtitles in various languages for movies and TV programs. Subtitle translations are valuable resources for cross-lingual studies and machine translation research. A …...

AbstractIn this paper, we introduce a coverage-based scoring function that discriminates between parallel and non-parallel sentences. When plugged into Bleualign, a state-of-the-art sentence aligner, our function improves both precision and …...

One major drawback of phrase-based translation is that it segments an input sen- tence into continuous phrases. To sup- port linguistically informed source discon- tinuity, in this paper we construct …...

AbstractConventional attention-based Neural Machine Translation (NMT) conducts dynamic alignment in generating the target sentence. By repeatedly reading the representation of source sentence, which keeps fixed after generated by the encoder …...

AbstractDomain adaptation is a major challenge when applying machine translation to practical tasks. In this paper, we present domain adaptation methods for machine translation that assume multiple domains. The proposed …...

AbstractAn interactive Question Answering (QA) system frequently encounters non-sentential (incomplete) questions. These non-sentential questions may not make sense to the system when a user asks them without the context of …...

AbstractWe present a method for translating texts between close language pairs. The method does not require parallel data, and it does not require the languages to be written in the …...

AbstractWe investigate the generation of one-sentence Wikipedia biographies from facts derived from Wikidata slot-value pairs. We train a recurrent neural network sequence-to-sequence model with attention to select facts and generate …...

AbstractIn this paper, we propose a new method for calculating the output layer in neural machine translation systems. The method is based on predicting a binary code for each word …...

AbstractWe investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this …...

AbstractThis paper describes the submission by the University of Sheffield to the SemEval 2017 Abstract Meaning Representation Parsing and Generation task (SemEval 2017 Task 9, Subtask 2). We cast language …...

AbstractIn neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality. However, in the neural generation setting, …...

AbstractWe propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself. We present a novel approach to NMT which generates the target sentence by …...

In this paper, we present evaluation corpora covering four genres for four language pairs that we harvested from the web in an automated fashion. We use these multi-genre benchmarks to …...

AbstractThis paper focuses on subword-based Neural Machine Translation (NMT). We hypothesize that in the NMT model, the appropriate subword units for the following three modules (layers) can differ: (1) the …...

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland …...

AbstractWe work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding …...

Automatic caption generation of images has gained significant interest. It gives rise to a lot of interesting image-related applications. For example, it could help in image/video retrieval and management of …...

AbstractText summarization is considered as a challenging task in the NLP community. The availability of datasets for the task of multilingual text summarization is rare, and such datasets are difficult …...

AbstractThe majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses. In this paper, we present an …...

Neural machine translation (NMT) sys- tems operate primarily on words (or sub- words), ignoring lower-level patterns of morphology. We present a character- aware decoder designed to capture such patterns when …...

AbstractProgrammers typically organize executable source code using high-level coding patterns or idiomatic structures such as nested loops, exception handlers and recursive blocks, rather than as individual code tokens. In contrast, …...

AbstractSoft-attention based Neural Machine Translation (NMT) models have achieved promising results on several translation tasks. These models attend all the words in the source sequence for each target token, which …...

AbstractA desideratum of high-quality translation systems is that they preserve meaning, in the sense that two sentences with different meanings should not translate to one and the same sentence in …...

AbstractRecent studies on AMR-to-text generation often formalize the task as a sequence-to-sequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequences. Graph structures are …...

AbstractNeural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios. Neural models have to be trained on large amounts of data and have been …...

AbstractSimultaneous translation is widely useful but remains one of the most difficult tasks in NLP. Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning. …...

AbstractEvaluation discrepancy and overcorrection phenomenon are two common problems in neural machine translation (NMT). NMT models are generally trained with word-level learning objective, but evaluated by sentence-level metrics. Moreover, the …...

AbstractThe commonly used framework for unsupervised machine translation builds initial translation models of both translation directions, and then performs iterative back-translation to jointly boost their translation performance. The initialization stage …...

AbstractMany automatic evaluation metrics have been proposed to score the overall quality of a response in open-domain dialogue. Generally, the overall quality is comprised of various aspects, such as relevancy, …...

Translating text that diverges from the training domain is a key challenge for machine trans- lation. Domain robustness—the generalization of models to unseen test domains—is low for both statistical (SMT) …...

AbstractExisting studies on multimodal neural machine translation (MNMT) have mainly focused on the effect of combining visual and textual modalities to improve translations. However, it has been suggested that the …...

AbstractWhile state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world’s languages …...

AbstractTransformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus …...

AbstractThe correct translation of named entities (NEs) still poses a challenge for conventional neural machine translation (NMT) systems. This study explores methods incorporating named entity recognition (NER) into NMT with …...

AbstractWe propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et …...

AbstractIn this paper we describe the systems developed at Ixa for our participation in WMT20 Biomedical shared task in three language pairs, en-eu, en-es and es-en. When defining our approach, …...

AbstractDocument-level machine translation focuses on the translation of entire documents from a source to a target language. It is widely regarded as a challenging task since the translation of the …...

AbstractMutual learning, where multiple agents learn collaboratively and teach one another, has been shown to be an effective way to distill knowledge for image classification tasks. In this paper, we …...

AbstractA Mathematical Word Problem (MWP) differs from a general textual representation due to the fact that it is comprised of numerical quantities and units, in addition to text. Therefore, MWP …...

AbstractDeep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT …...

AbstractIn this work, we develop SimulSpeech, an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently. SimulSpeech consists of a …...

AbstractThis paper describes the Tencent AI Lab submission of the WMT2020 shared task on biomedical translation in four language directions: German<->English, English<->German, Chinese<->English and English<->Chinese. We implement our system with …...

AbstractIn automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-encoder …...

Bilingual word embeddings (BWEs) facilitate the translation of single source language words to single target language words. However, often a single source word must be translated using two target words. …...

AbstractWe participate in the WMT 2020 shared newstranslation task on Chinese→English. Our system is based on the Transformer (Vaswaniet al., 2017a) with effective variants and the DTMT (Meng and Zhang, …...

AbstractWe propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words …...

AbstractThe success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural …...

AbstractThe discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms …...

AbstractDocument-level MT models are still far from satisfactory. Existing work extend translation unit from single sentence to multiple sentences. However, study shows that when we further enlarge the translation unit …...

AbstractA recent topic of research in natural language generation has been the development of automatic response generation modules that can automatically respond to a user’s utterance in an empathetic manner. …...

AbstractGenerating open-domain conversational responses in the desired style usually suffers from the lack of parallel data in the style. Meanwhile, using monolingual stylistic data to increase style intensity often leads …...

AbstractKnowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original …...

AbstractThis paper describes the SEBAMAT contribution to the 2021 WMT Similar Language Translation shared task. Using the Marian neural machine translation toolkit, translation systems based on Google’s transformer architecture were …...

AbstractEncoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or …...

AbstractThis paper describes Tencent Translation systems for the WMT21 shared task. We participate in the news translation task on three language pairs: Chinese-English, English-Chinese and German-English. Our systems are built …...

AbstractOne key ingredient of neural machine translation is the use of large datasets from different domains and resources (e.g. Europarl, TED talks). These datasets contain documents translated by professional translators …...

AbstractUnsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has achieved comparable performance against supervised machine translation. However, it still suffers from data-scarce domains. To address this issue, …...

In this paper, we define a sentence re- generation task: re-generate a sentence given a set of sentences that cover it. Due to the absence of a dataset to perform …...

AbstractThis paper describes Microsoft’s submission to the first shared task on sign language translation at WMT 2022, a public competition tackling sign language to spoken language translation for Swiss German …...

AbstractThe phenomenon of zero pronoun (ZP) has attracted increasing interest in the machine translation (MT) community due to its importance and difficulty. However, previous studies generally evaluate the quality of …...

AbstractThis paper describes Amazon Alexa AI’s implementation for the IWSLT 2022 shared task on formality control. We focus on the unconstrained and supervised task for en→hi (Hindi) and en→ja (Japanese) …...

AbstractBack-translation has been proven to be effective in unsupervised domain adaptation of neural machine translation (NMT). However, the existing back-translation methods mainly improve domain adaptability by generating in-domain pseudo-parallel data …...

AbstractK-Nearest Neighbor Neural Machine Translation (kNNMT) successfully incorporates external corpus by retrieving word-level representations at test time. Generally, kNNMT borrows the off-the-shelf context representation in the translation task, e.g., the …...

AbstractAvailability of the user reviews in vernacular languages is helpful for the users to get information regarding the products. Since most of the e-commerce websites allow the reviews in English …...

AbstractCan machines know what twin prime is? From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to …...

AbstractRecent studies have shown that the multi-encoder models are agnostic to the choice of context and the context encoder generates noise which helps in the improvement of the models in …...

AbstractIn this paper, we describe the implementations of our systems for the SemEval-2023 Task 5 ‘Clickbait Spoiling’, which involves the classification of clickbait posts in sub-task 1 and the spoiler …...

AbstractIn this paper, we present a novel approach for data-to-text generation that addresses the limitations of current methods that primarily focus on specific types of structured data. Our proposed method …...

AbstractTraining end-to-end speech translation (ST) systems requires sufficiently large-scale data, which is unavailable for most language pairs and domains. One practical solution to the data scarcity issue is to convert …...

AbstractThis paper describes the speech translation system submitted as part of the IWSLT 2023 shared task on low resource speech translation. The low resource task aids in building models for …...

AbstractThe decoder in simultaneous neural machine translation receives limited information from the source while having to balance the opposing requirements of latency versus translation quality. In this paper, we use …...

AbstractDecoding text stimuli from cognitive signals (e.g. fMRI) enhances our understanding of the human language system, paving the way for building versatile Brain-Computer Interface. However, existing studies largely focus on …...