Identifying Semantic Divergences in Parallel Text without Annotations

Recognizing that even correct translations are not always semantically equivalent, we automatically detect meaning divergences in parallel sentence pairs with a deep neural model of bilingual semantic similarity which can be trained for any parallel corpus without any manual annotation. We show that our semantic model detects divergences more accurately than models based on surface features derived from word alignments, and that these divergences matter for neural machine translation.

• Publication year

  2018

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2018-03-29

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/N18-1136arXiv 1803.11112
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Achieving Human Parity on Automatic Chinese to English News Translation

  2018cited by this paper
• Stronger Baselines for Trustable Results in Neural Machine Translation

  2017cited by this paper
• Sockeye: A Toolkit for Neural Machine Translation

  2017cited by this paper
• Synthetic and Natural Noise Both Break Neural Machine Translation

  2017cited by this paper
• Learning Joint Multilingual Sentence Representations with Neural Machine Translation

  2017cited by this paper
• Empirical Investigation of Optimization Algorithms in Neural Machine Translation

  2017influential reference
• Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation

  2017influential reference
• An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification

  2017cited by this paper
• WMT17 Quality Estimation Shared Task Training and Development Data

  2016cited by this paper
• SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation

  2016cited by this paper
• FBK’s Neural Machine Translation Systems for IWSLT 2016

  2016cited by this paper
• Bilingual Methods for Adaptive Training Data Selection for Machine Translation

  2016cited by this paper
• OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles

  2016cited by this paper
• Novel elicitation and annotation schemes for sentential and sub-sentential alignments of bitexts

  2016influential reference
• CNRC at SemEval-2016 Task 1: Experiments in Crosslingual Semantic Textual Similarity

  2016cited by this paper
• Microsoft Speech Language Translation (MSLT) Corpus: The IWSLT 2016 release for English, French and German

  2016cited by this paper
• Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement

  2016cited by this paper
• Bilingual Word Representations with Monolingual Quality in Mind

  2015influential reference
• Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

  2015cited by this paper
• Neural Machine Translation of Rare Words with Subword Units

  2015cited by this paper
• Exploration of Inter- and Intralingual Variation of Discourse Phenomena

  2015cited by this paper
• Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

  2015cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• The CMU Machine Translation Systems at WMT 2014

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Assessing the Discourse Factors that Influence the Quality of Machine Translation

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• SemEval-2014 Task 10: Multilingual Semantic Textual Similarity

  2014cited by this paper
• ALTN: Word Alignment Features for Cross-lingual Textual Entailment

  2013cited by this paper
• ECNUCS: Recognizing Cross-lingual Textual Entailment Using Multiple Text Similarity and Text Difference Measures

  2013cited by this paper
• Dirt Cheap Web-Scale Parallel Text from the Common Crawl

  2013cited by this paper
• Semeval-2013 Task 8: Cross-lingual Textual Entailment for Content Synchronization

  2013cited by this paper
• Semeval-2012 Task 8: Cross-lingual Textual Entailment for Content Synchronization

  2012cited by this paper
• Soft Cardinality + ML: Learning Adaptive Similarity Functions for Cross-lingual Textual Entailment

  2012cited by this paper
• Automatic Parallel Fragment Extraction from Noisy Data

  2012cited by this paper
• WIT3: Web Inventory of Transcribed and Translated Talks

  2012influential reference
• The Impact of Sentence Alignment Errors on Phrase-Based Machine Translation Performance

  2012cited by this paper
• Bitext Alignment

  2011cited by this paper
• Information Theory and Statistics

  2011cited by this paper
• Translationese and Its Dialects

  2011cited by this paper
• Rectified Linear Units Improve Restricted Boltzmann Machines

  2010cited by this paper
• Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment

  2010cited by this paper
• Creating a Bi-lingual Entailment Corpus through Translations with Mechanical Turk: $100 for a 10-day Rush

  2010cited by this paper
• Machine translation evaluation versus quality estimation

  2010cited by this paper
• Composition in Distributional Models of Semantics

  2010cited by this paper
• On the Use of Comparable Corpora to Improve SMT performance

  2009cited by this paper
• Improved Sentence Alignment for Movie Subtitles

  2007cited by this paper
• Alignment by Agreement

  2006cited by this paper
• Extracting Parallel Sub-Sentential Fragments from Non-Parallel Corpora

  2006cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005cited by this paper
• Improving Machine Translation Performance by Exploiting Non-Parallel Corpora

  2005influential reference
• Multi-level Bootstrapping For Extracting Parallel Sentences From a Quasi-Comparable Corpus

  2004cited by this paper
• Statistical Significance Tests for Machine Translation Evaluation

  2004cited by this paper
• Handling translation divergences: combining statistical and symbolic techniques in generation-heavy machine translation

  2002cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Near-synonymy and the structure of lexical knowledge

  1995cited by this paper
• Machine Translation Divergences: A Formal Description and Proposed Solution

  1994influential reference
• Statistical significance tests.

  1982cited by this paper
• Information Theory and Statistics

  1960cited by this paper

• Exploiting Multi-Level Data Uncertainty for Japanese-Chinese Neural Machine Translation

  2025cites this paper
• To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation

  2024cites this paper
• Analysing Translation Artifacts: A Comparative Study of LLMs, NMTs, and Human Translations

  2024cites this paper
• Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation

  2023cites this paper
• Bridging Background Knowledge Gaps in Translation with Automatic Explicitation

  2023cites this paper
• Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences

  2023cites this paper
• X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs

  2023cites this paper
• Measuring Fine-Grained Semantic Equivalence with Abstract Meaning Representation

  2022cites this paper
• In-context Examples Selection for Machine Translation

  2022cites this paper
• Data Cartography for Low-Resource Neural Machine Translation

  2022cites this paper
• Improved corpus base English to Hindi language translation sequence-based deep learning approach

  2021cites this paper
• Classifying Divergences in Cross-lingual AMR Pairs

  2021cites this paper
• The UMD Submission to the Explainable MT Quality Estimation Shared Task: Combining Explanation Models with Sequence Labeling

  2021cites this paper
• BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation

  2021cites this paper
• Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation

  2021cites this paper
• Neural Machine Translation between similar South-Slavic languages

  2020cites this paper
• Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences

  2020cites this paper
• Generating Diverse Translations via Weighted Fine-tuning and Hypotheses Filtering for the Duolingo STAPLE Task

  2020cites this paper
• On the differences between human translations

  2020cites this paper
• Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank

  2020influential citation
• Domain Divergences: A Survey and Empirical Analysis

  2020cites this paper
• Neural Machine Translation for translating into Croatian and Serbian

  2020cites this paper
• K-SNACS: Annotating Korean Adposition Semantics

  2020cites this paper
• Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models

  2020cites this paper
• Self-Supervised Learning for Pairwise Data Refinement

  2020cites this paper
• Handling Divergent Reference Texts when Evaluating Table-to-Text Generation

  2019cites this paper
• Towards Recognizing Phrase Translation Processes: Experiments on English-French

  2019cites this paper
• Classification automatique des procédés de traduction (Automatic Classification of Translation Processes)

  2019cites this paper
• Optimizing Data Usage via Differentiable Rewards

  2019cites this paper
• Controlling Neural Machine Translation Formality with Synthetic Supervision

  2019cites this paper
• Misalignment Detection for Web-Scraped Corpora: A Supervised Regression Approach

  2019cites this paper
• Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection

  2018cites this paper
• Multi-Task Neural Models for Translating Between Styles Within and Across Languages

  2018cites this paper
• Analyzing Knowledge Distillation in Neural Machine Translation

  2018cites this paper
• Fixing Translation Divergences in Parallel Corpora for Neural MT

  2018cites this paper
• . Automatic Explicitation to Bridge the Back-ground Knowledge Gap in Translation and its Evaluation with Multilingual QA . Empirical Methods in Natural Language Processing , 2023, 9 pages

  year unknowncites this paper