Syntax-based Rewriting for Simultaneous Machine Translation

Divergent word order between languages causes delay in simultaneous machine translation. We present a sentence rewriting method that generates more monotonic translations to improve the speedaccuracy tradeoff. We design grammaticality and meaning-preserving syntactic transformation rules that operate on constituent parse trees. We apply the rules to reference translations to make their word order closer to the source language word order. On Japanese-English translation (two languages with substantially different structure), incorporating the rewritten, more monotonic reference translation into a phrase-based machine translation system enables better translations faster than a baseline system that only uses gold reference translations.

• Publication year

  2015

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  2015-09-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/D15-1006
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Japanese to English Machine Translation using Preordering and Compositional Distributed Semantics

  2014cited by this paper
• Frame-Semantic Parsing

  2014cited by this paper
• Don't Until the Final Verb Wait: Reinforcement Learning for Simultaneous Machine Translation

  2014cited by this paper
• Optimizing Segmentation Strategies for Simultaneous Speech Translation

  2014cited by this paper
• Collection of a Simultaneous Translation Corpus for Comparative Analysis

  2014cited by this paper
• Constructing a speech translation system using simultaneous interpretation data

  2013cited by this paper
• Simple, lexicalized choice of translation timing for simultaneous speech translation

  2013influential reference
• Segmentation Strategies for Streaming Speech Translation

  2013cited by this paper
• Two-Stage Pre-ordering for Japanese-to-English Statistical Machine Translation

  2013cited by this paper
• Real-time Incremental Speech-to-Speech Translation of Dialogs

  2012cited by this paper
• Batch Tuning Strategies for Statistical Machine Translation

  2012cited by this paper
• COGNITIVE THEORY OF SIMULTANEOUS INTERPRETING AND TRAINING

  2011influential reference
• Fill-up versus interpolation methods for phrase-based SMT adaptation

  2011cited by this paper
• Automatic Evaluation of Translation Quality for Distant Language Pairs

  2010influential reference
• Spoken language translation from parallel speech audio: Simultaneous interpretation as SLT training data

  2010cited by this paper
• Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages

  2009cited by this paper
• A Simple and Effective Hierarchical Phrase Reordering Model

  2008cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• An Approach to Corpus-Based Interpreting Studies: Developing EPIC (European Parliament Interpreting Corpus)

  2007cited by this paper
• Simultaneous translation of lectures and speeches

  2007cited by this paper
• Collection of Simultaneous Interpreting Patterns by Using Bilingual Spoken Monologue Corpus

  2006cited by this paper
• Clause Restructuring for Statistical Machine Translation

  2005cited by this paper
• A Systematic Comparison of Various Statistical Alignment Models

  2003cited by this paper
• Reliable Measures for Aligning Japanese-English News Articles and Sentences

  2003cited by this paper
• Accurate Unlexicalized Parsing

  2003cited by this paper
• Bilingual Spoken Monologue Corpus for Simultaneous Machine Interpretation Research

  2002cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002influential reference
• On the use of compensatory strategies in simultaneous interpretation

  2000cited by this paper
• Sync/Trans: Simultaneous Machine Interpretation between English and Japanese

  1999cited by this paper
• Using text mappings in teaching consecutive interpreting

  1997cited by this paper

• Investigating Omission as a Latency Reduction Strategy in Simultaneous Speech Translation

  2025cites this paper
• Simul-MuST-C: Simultaneous Multilingual Speech Translation Corpus Using Large Language Model

  2024cites this paper
• Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation

  2024cites this paper
• NAIST-SIC-Aligned: An Aligned English-Japanese Simultaneous Interpretation Corpus

  2024cites this paper
• Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair

  2024cites this paper
• NAIST-SIC-Aligned: Automatically-Aligned English-Japanese Simultaneous Interpretation Corpus

  2023cites this paper
• PERSONAL STATEMENT ON MY RESEARCH: EVALUATING AND ENABLING HUMAN–AI COLLABORATION

  2023cites this paper
• Non-autoregressive Streaming Transformer for Simultaneous Translation

  2023cites this paper
• Anticipation-Free Training for Simultaneous Machine Translation

  2022cites this paper
• Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation

  2022cites this paper
• RESEARCH PROPOSAL: EVALUATING AND ENABLING HUMAN–AI COLLABORATION

  2022cites this paper
• RESEARCH PROPOSAL: EVALUATING AND ENABLING HUMAN–AI COLLABORATION

  2022cites this paper
• Improving Simultaneous Machine Translation with Monolingual Data

  2022influential citation
• Anticipation-free Training for Simultaneous Translation

  2022cites this paper
• Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English

  2020influential citation
• Efficient Wait-k Models for Simultaneous Machine Translation

  2020cites this paper
• Improving Simultaneous Translation with Pseudo References

  2020cites this paper
• An Attentive Recurrent Model for Incremental Prediction of Sentence-final Verbs

  2020cites this paper
• Generating Syntactically Variant Text Adversaries

  2020cites this paper
• Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings

  2020cites this paper
• Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters’ Décalage

  2019cites this paper
• Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation

  2019cites this paper
• Simultaneous Translation using Optimized Segmentation

  2018cites this paper
• STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework

  2018cites this paper
• Incremental Natural Language Processing: Challenges, Strategies, and Evaluation

  2018influential citation
• Measuring the Limit of Semantic Divergence for English Tweets.

  2017cites this paper
• Dynamic Information Acquisition for Efficient Prediction

  2017cites this paper
• Incremental Prediction and Decision-Making for Simultaneous Machine Translation

  2017influential citation
• Generating Sentences by Editing Prototypes

  2017cites this paper
• Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback

  2017cites this paper
• Left-to-Right Hierarchical Phrase-based Machine Translation

  2016cites this paper
• Sequential Decisions and Predictions in Natural Language Processing

  2016influential citation
• Dynamic Transcription for Low-Latency Speech Translation

  2016cites this paper
• Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation

  2016cites this paper
• Training Data Annotation for Segmentation Classification in Simultaneous Translation

  2016cites this paper
• Sentence Rewriting for Semantic Parsing

  2016cites this paper
• Learning segmentations that balance latency versus quality in spoken language translation

  2015cites this paper