Back Translation

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 …...

AbstractThis paper describes the submission of the University of Edinburgh team to the IWSLT MT task for TED talks. We took part in four translation directions, en-de, de-en, en-fr, and …...

In this paper, we describe our submissions to the WMT17 Multimodal Translation Task. For Task 1 (multimodal translation), our best scoring system is a purely textual neural translation of the …...

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 …...

In this paper the UHH submission to the WMT17 Metrics Shared Task is presented, which is based on sequence and tree ker- nel functions applied to the reference and candidate …...

AbstractWe propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to …...

AbstractA prerequisite for training corpus-based machine translation (MT) systems – either Statistical MT (SMT) or Neural MT (NMT) – is the availability of high-quality parallel data. This is arguably more …...

AbstractTelugu is the fifteenth most commonly spoken language in the world with an estimated reach of 75 million people in the Indian subcontinent. At the same time, it is a …...

AbstractNeural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, …...

AbstractNeural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. …...

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 …...

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 …...

AbstractZero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, …...

AbstractIn this paper, we propose a multilingual unsupervised NMT scheme which jointly trains multiple languages with a shared encoder and multiple decoders. Our approach is based on denoising autoencoding of …...

AbstractMachine Translation systems have drastically improved over the years for several language pairs. Monolingual data is often used to generate synthetic sentences to augment the training data which has shown …...

AbstractRecent work in Neural Machine Translation (NMT) has shown significant quality gains from noised-beam decoding during back-translation, a method to generate synthetic parallel data. We show that the main role …...

AbstractIn neural machine translation (NMT), monolingual data are usually exploited through a so-called back-translation: sentences in the target language are translated into the source language to synthesize new parallel data. …...

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 …...

AbstractSuggestion mining task aims to extract tips, advice, and recommendations from unstructured text. The task includes many challenges, such as class imbalance, figurative expressions, context dependency, and long and complex …...

AbstractIn this paper, we present a corpus for use in automatic readability assessment and automatic text simplification for German, the first of its kind for this language. The corpus is …...

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 …...

AbstractIn this paper, we describe our systems submitted to the very low resource supervised translation task at WMT20. We participate in both translation directions for Upper Sorbian-German language pair. Our …...

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 …...

AbstractSocial media platforms, online news commenting spaces, and many other public forums have become widely known for issues of abusive behavior such as cyber-bullying and personal attacks. In this paper, …...

AbstractLow-resource machine translation suffers from the scarcity of training data and the unavailability of standard evaluation sets. While a number of research efforts target the former, the unavailability of evaluation …...

AbstractThe quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice of metric is important, the nature …...

AbstractThe extraction of labels from radiology text reports enables large-scale training of medical imaging models. Existing approaches to report labeling typically rely either on sophisticated feature engineering based on medical …...

AbstractThis paper describes CUNI submission to the WMT 2020 News Translation Shared Task for the low-resource scenario Inuktitut–English in both translation directions. Our system combines transfer learning from a Czech–English …...

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 …...

AbstractThis paper describes our system submission to WMT20 shared task on similar language translation. We examined the use of documentlevel neural machine translation (NMT) systems for low-resource, similar language pair …...

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 …...

AbstractUnsupervised neural machine translation (NMT) utilizes only monolingual data for training. The quality of back-translated data plays an important role in the performance of NMT systems. In back-translation, all generated …...

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 …...

AbstractTask-agnostic forms of data augmentation have proven widely effective in computer vision, even on pretrained models. In NLP similar results are reported most commonly for low data regimes, non-pretrained models, …...

AbstractGiven a sentence and its relevant answer, how to ask good questions is a challenging task, which has many real applications. Inspired by human’s paraphrasing capability to ask questions of …...

AbstractThis paper presents our work in the WMT 2020 News Translation Shared Task. We participate in 3 language pairs including Zh/En, Km/En, and Ps/En and in both directions under the …...

AbstractThis paper describes Infosys’s submission to the WMT20 Similar Language Translation shared task. We participated in Indo-Aryan language pair in the language direction Hindi to Marathi. Our baseline system is …...

AbstractIn this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. One common and effective strategy for this case is exploiting …...

AbstractThis paper describes the LIT Team’s submission to the IWSLT2020 open domain translation task, focusing primarily on Japanese-to-Chinese translation direction. Our system is based on the organizers’ baseline system, but …...

AbstractMachine translation provides powerful methods to convert text between languages, and is therefore a technology enabling a multilingual world. An important part of communication, however, takes place at the non-propositional …...

AbstractBack-translation is a widely used data augmentation technique which leverages target monolingual data. However, its effectiveness has been challenged since automatic metrics such as BLEU only show significant improvements for …...

AbstractQuestion Generation (QG) is fundamentally a simple syntactic transformation; however, many aspects of semantics influence what questions are good to form. We implement this observation by developing Syn-QG, a set …...

AbstractIn this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts. Such NMT systems better translate human-produced …...

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 …...

AbstractThis paper describes the DeepMind submission to the Chinese→English constrained data track of the WMT2020 Shared Task on News Translation. The submission employs a noisy channel factorization as the backbone …...

AbstractWe describe the University of Edinburgh’s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut. We use the …...

AbstractThe scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; …...

The success of Neural Machine Translation (NMT) largely depends on the availability of large bitext training corpora. Due to the lack of such large corpora in low-resource language pairs, NMT …...

AbstractThis paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). In this work, we aim to build a …...

AbstractStyle transfer aims to rewrite a source text in a different target style while preserving its content. We propose a novel approach to this task that leverages generic resources, and …...

AbstractThis paper describes the Global Tone Communication Co., Ltd.’s submission of the WMT21 shared news translation task. We participate in six directions: English to/from Hausa, Hindi to/from Bengali and Zulu …...

AbstractBack-translation (BT) of target monolingual corpora is a widely used data augmentation strategy for neural machine translation (NMT), especially for low-resource language pairs. To improve effectiveness of the available BT …...

AbstractThis paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task. We participate in 7 language pairs, including Zh/En, De/En, Ja/En, Ha/En, …...

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 system paper describes an end-to-end NMT pipeline for the Japanese ↔ English news translation task as submitted to WMT 2021, where we explore the efficacy of techniques such as …...

AbstractWe present a simple and effective pretraining strategy – bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune …...

AbstractThis paper describes Kakao Enterprise’s submission to the WMT21 shared Machine Translation using Terminologies task. We integrate terminology constraints by pre-training with target lemma annotations and fine-tuning with exact target …...

Improving the robustness of neural machine translation models on variations of input sen- tences is an active area of research. In this paper, we propose a simple data augmenta- tion …...

AbstractWe present Miðeind’s submission for the English→Icelandic and Icelandic→English subsets of the 2021 WMT news translation task. Transformer-base models are trained for translation on parallel data to generate backtranslations teratively. …...

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 …...

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 …...

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 …...

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 …...

AbstractThis paper describes the Fujitsu DMATH systems used for WMT 2021 News Translation and Biomedical Translation tasks. We focused on low-resource pairs, using a simple system. We conducted experiments on …...

AbstractThis paper describes Mininglamp neural machine translation systems of the WMT2021 news translation tasks. We have participated in eight directions translation tasks for news text including Chinese to/from English, Hausa …...

AbstractWhile we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific …...

AbstractUnsupervised Data Augmentation (UDA) is a semisupervised technique that applies a consistency loss to penalize differences between a model’s predictions on (a) observed (unlabeled) examples; and (b) corresponding ‘noised’ examples …...

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 …...

AbstractThis paper introduces WeChat AI’s participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. Our systems are based on the Transformer (Vaswani et al., 2017) …...

AbstractThis paper introduces the joint submission of the Beijing Jiaotong University and WeChat AI to the WMT’22 chat translation task for English-German. Based on the Transformer, we apply several effective …...

AbstractBack-translation is a well established approach to improve the performance of Neural Machine Translation (NMT) systems when large monolingual corpora of the target language and domain are available. Recently, diverse …...

AbstractPreservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly-specialized projects, where there is hardly …...

AbstractGTCOM participates in five directions: English to/from Ukrainian, Ukrainian to/from Czech, English to Chinese and English to Croatian. Our submitted systems are unconstrained and focus on backtranslation, multilingual translation model …...

AbstractThis paper describes the translation systems trained by Huawei translation services center (HW-TSC) for the WMT22 biomedical translation task in five language pairs: English↔German (en↔de), English↔French (en↔fr), English↔Chinese (en↔zh), English↔Russian …...

AbstractThis paper describes the submissions of Huawei Translation Services Center (HW-TSC) to WMT22 chat translation shared task on English-Germany (en-de) bidirection with results of zore-shot and few-shot tracks. We use …...

AbstractThis paper presents the submissions of Huawei Translate Services Center (HW-TSC) to the WMT 2022 General Machine Translation Shared Task. We participate in 6 language pairs, including Zh↔En, Ru↔En, Uk↔En, …...

AbstractDictionary-based data augmentation techniques have been used in the field of domain adaptation to learn words that do not appear in the parallel training data of a machine translation model. …...

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 …...

AbstractThis paper details the Johns Hopkins speech translation (ST) system used in the IWLST2022 dialect speech translation task. Our system uses a cascade of automatic speech recognition (ASR) and machine …...

AbstractWe present LINGUIST, a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST), via fine-tuning AlexaTM 5B, a 5-billion-parameter multilingual sequence-to-sequence (seq2seq) model, on a flexible instruction …...

In this paper, we focus on improving the intent recognition for a conversational agent. For lan- guages other than English, labeled data needed for training is often limited. Limitations rise …...

AbstractAugmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation …...

AbstractBack translation (BT) is one of the most significant technologies in NMT research fields. Existing attempts on BT share a common characteristic: they employ either beam search or random sampling …...

AbstractThis paper describes submission to the WMT 2022 Quality Estimation shared task (Task 1: sentence-level quality prediction). We follow a simple and intuitive approach, which consists of estimating MT quality …...

AbstractIn recent years, large multilingual pre-trained neural machine translation model research has grown and it is common for these models to be publicly available for usage and fine-tuning. Low-resource languages …...

AbstractThis paper describes AISP-SJTU’s participation in WMT 2022 shared general MT task. In this shared task, we participated in four translation directions: English-Chinese, Chinese-English, English-Japanese and Japanese-English. Our systems are …...

AbstractThis paper describes the NiuTrans neural machine translation systems of the WMT22 General MT constrained task. We participate in four directions, including Chinese→English, English→Croatian, and Livonian↔English. Our models are based …...

AbstractThe University of Edinburgh participated in the WMT22 shared task on code-mixed translation. This consists of two subtasks: i) generating code-mixed Hindi/English (Hinglish) text generation from parallel Hindi and English …...

AbstractData augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, …...

AbstractZero-shot paraphrase generation has drawn much attention as the large-scale high-quality paraphrase corpus is limited. Back-translation, also known as the pivot-based method, is typical to this end. Several works leverage …...

AbstractThe success of end-to-end speech-to-text translation (ST) is often achieved by utilizing source transcripts, e.g., by pre-training with automatic speech recognition (ASR) and machine translation (MT) tasks, or by introducing …...

AbstractPersuasion techniques detection in news in a multi-lingual setup is non-trivial and comes with challenges, including little training data. Our system successfully leverages (back-)translation as data augmentation strategies with multi-lingual …...

AbstractVisual-Word Sense Disambiguation (V-WSD) entails resolving the linguistic ambiguity in a text by selecting a clarifying image from a set of (potentially misleading) candidates. In this paper, we address V-WSD …...

AbstractSign language gloss translation aims to translate the sign glosses into spoken language texts, which is challenging due to the scarcity of labeled gloss-text parallel data. Back translation (BT), which …...

AbstractFor many languages, machine translation progress is hindered by the lack of reliable training data. Models are trained on whatever pre-existing datasets may be available and then augmented with synthetic …...

AbstractBack Translation (BT) is widely used in the field of machine translation, as it has been proved effective for enhancing translation quality. However, BT mainly improves the translation of inputs …...

AbstractThe application of machine translation in the field of poetry has always presented significant challenges. Conventional machine translation techniques are inadequate for capturing and translating the unique style of poetry. …...

AbstractGraph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for knowledge graphs. Existing unsupervised approaches become suitable candidates for jointly learning the two tasks due to their …...

AbstractWhile paraphrasing is a promising approach for data augmentation in classification tasks, its effect on named entity recognition (NER) is not investigated systematically due to the difficulty of span-level label …...