Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation

The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in translation quality when translating long sentences, unlike existing phrase-based translation systems. In this paper, we propose a way to address this issue by automatically segmenting an input sentence into phrases that can be easily translated by the neural network translation model. Once each segment has been independently translated by the neural machine translation model, the translated clauses are concatenated to form a final translation. Empirical results show a significant improvement in translation quality for long sentences.

• Publication year

  2014

• Venue

  SSST@EMNLP

• Publication date

  2014-09-03

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.3115/v1/W14-4009arXiv 1409.1257
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Proceedings of SSST-9, Ninth Workshop on Syntax, Semantics and Structure in Statistical Translation

  2015cited by this paper
• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  2014influential reference
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014influential reference
• Generating Sequences With Recurrent Neural Networks

  2013cited by this paper
• Audio Chord Recognition with Recurrent Neural Networks

  2013cited by this paper
• Recurrent Continuous Translation Models

  2013cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• Domain Adaptation via Pseudo In-Domain Data Selection

  2011cited by this paper
• Statistical Phrase-Based Translation

  2003cited by this paper
• Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL)

  2002cited by this paper

• Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation

  2025cites this paper
• Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT

  2025cites this paper
• BASSET: Enhancing Binary Code Clone Searching through Multi-Level Hybrid Semantic Indexing

  2025cites this paper
• Evaluating Machine Translation Models for English-Hindi Language Pairs: A Comparative Analysis

  2025cites this paper
• JIBON++: AI Enabled Intelligent Voice Assistant for Blind People Understanding Negative Sentiments

  2025cites this paper
• WikiSplit++: Easy Data Refinement for Split and Rephrase

  2024cites this paper
• Neural Machine Translation For Low Resource Languages

  2023cites this paper
• TRIP: Accelerating Document-level Multilingual Pre-training via Triangular Document-level Pre-training on Parallel Data Triplets

  2023cites this paper
• The Source Code Comment Generation Based on Deep Reinforcement Learning and Hierarchical Attention

  2023cites this paper
• Deep Learning for Natural Language Processing: A Survey

  2023cites this paper
• Virtual-diagnostic-based time stamping for ultrafast electron diffraction

  2023cites this paper
• Reinforcement-Learning-Guided Source Code Summarization Using Hierarchical Attention

  2022cites this paper
• Improved Long-Form Spoken Language Translation with Large Language Models

  2022cites this paper
• Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models

  2022cites this paper
• Towards Multilingual Transitivity and Bidirectional Multilingual Agreement for Multilingual Document-level Machine Translation

  2022cites this paper
• Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation

  2022cites this paper
• Adversarial Machine Learning in Text Processing: A Literature Survey

  2022cites this paper
• Text Compression-Aided Transformer Encoding

  2021cites this paper
• Adversarial Machine Learning in Text Analysis and Generation

  2021cites this paper
• Robust Neural Language Translation Model Formulation using Seq2seq approach

  2021cites this paper
• BiSECT: Learning to Split and Rephrase Sentences with Bitexts

  2021cites this paper
• Effectiveness of Syntactic Dependency Information for Higher-Order Syntactic Attention Network

  2021cites this paper
• Better Chinese Sentence Segmentation with Reinforcement Learning

  2021cites this paper
• Designing and Implementing Conversational Intelligent Chat-bot Using Natural Language Processing

  2021cites this paper
• POS-Tagging based Neural Machine Translation System for European Languages using Transformers

  2021cites this paper
• Central Kurdish machine translation: First large scale parallel corpus and experiments

  2021cites this paper
• G-Transformer for Document-Level Machine Translation

  2021cites this paper
• Clause Attention based on Signal Words Division

  2021cites this paper
• Low-Resource Neural Machine Translation for Southern African Languages

  2021cites this paper
• Fine-Tuning Sign Language Translation Systems Through Deep Reinforcement Learning

  2021cites this paper
• A comparative study of state-of-the-art speech recognition models for English and Dutch

  2020cites this paper
• Enhancements to the Sequence-to-Sequence-Based Natural Answer Generation Models

  2020cites this paper
• The Roles of Language Models and Hierarchical Models in Neural Sequence-to-Sequence Prediction

  2020cites this paper
• Automatic Canonical Utterance Generation for Task-Oriented Bots from API Specifications

  2020cites this paper
• Universal Vector Neural Machine Translation With Effective Attention

  2020cites this paper
• Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition Without Length Bias

  2020cites this paper
• On Long-Tailed Phenomena in Neural Machine Translation

  2020cites this paper
• Traitement automatique des langues et génération automatique d'exercices de grammaire. (Automatic language processing and automatic generation of grammar exercises)

  2020cites this paper
• Semantic Structural Decomposition for Neural Machine Translation

  2020influential citation
• Long Sentence Preprocessing in Neural Machine Translation

  2019cites this paper
• Incorporating Source-Side Phrase Structures into Neural Machine Translation

  2019cites this paper
• Context in Neural Machine Translation: A Review of Models and Evaluations

  2019cites this paper
• Neural Machine Translation: A Review

  2019cites this paper
• Cyberbullying Detection for Online Games Chat Logs using Deep Learning

  2019cites this paper
• NLP AND MACHINE LEARNING TECHNIQUES TO DETECT ONLINE HARASSMENT ON SOCIAL NETWORKING PLATFORMS

  2019cites this paper
• Fast and Efficient Parallel Alignment Model for Aligning both Long and Short Sentences

  2019cites this paper
• Split First and Then Rephrase: Hierarchical Generation for Sentence Simplification

  2019cites this paper
• Naive Regularizers for Low-Resource Neural Machine Translation

  2019influential citation
• Abstractive Sentence Compression with Event Attention

  2019cites this paper
• Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion

  2019cites this paper
• AI-Chatbot Using Deep Learning to Assist the Elderly

  2019cites this paper
• Character Decomposition for Japanese-Chinese Character-Level Neural Machine Translation

  2019cites this paper
• Evaluation of the impact of controlled language on neural machine translation compared to other MT architectures

  2019cites this paper
• Explicit Sentence Compression for Neural Machine Translation

  2019cites this paper
• Split and Rephrase: Better Evaluation and Stronger Baselines

  2018cites this paper
• 32 15 v 3 [ cs . C L ] 1 4 D ec 2 01 4 Sequence to Sequence Learning with Neural Networks

  2018cites this paper
• A Hierarchy-to-Sequence Attentional Neural Machine Translation Model

  2018cites this paper
• Machine Translation and Self-post-editing for Academic Writing Support: Quality Explorations

  2018cites this paper
• Generating Abstractive Summaries Using Sequence to Sequence Attention Model

  2018cites this paper
• From Feature to Paradigm: Deep Learning in Machine Translation (Extended Abstract)

  2018cites this paper
• Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model

  2018cites this paper
• Higher-Order Syntactic Attention Network for Longer Sentence Compression

  2018cites this paper
• Neural versus phrase-based MT quality: An in-depth analysis on English-German and English-French

  2018cites this paper
• Machine Translation at Booking.com: Journey and Lessons Learned

  2017cites this paper
• Towards Document-Level Neural Machine Translation

  2017cites this paper
• A Comparative Quality Evaluation of PBSMT and NMT using Professional Translators

  2017cites this paper
• A Comparative Quality Evaluation of PBSMT and NMT using Professional Translators

  2017cites this paper
• Source sentence simplification for statistical machine translation

  2017cites this paper
• Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores

  2017cites this paper
• Neural Machine Translation on scarce-resource condition: A case-study on Persian-English

  2017cites this paper
• Αναδρομικά Νευρωνικά Δίκτυα και αυτόματη παραγωγή Hashtag από Tweet του Twitter

  2017cites this paper
• Six Challenges for Neural Machine Translation

  2017cites this paper
• Tree-to-Sequence Attentional Neural Machine Translation

  2016cites this paper
• Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers

  2016cites this paper
• A survey of voice translation methodologies — Acoustic dialect decoder

  2016cites this paper
• Neural versus Phrase-Based Machine Translation Quality: a Case Study

  2016cites this paper
• Length bias in Encoder Decoder Models and a Case for Global Conditioning

  2016cites this paper
• Automatic Long Sentence Segmentation for Neural Machine Translation

  2016cites this paper
• A Hierarchical Neural Autoencoder for Paragraphs and Documents

  2015cites this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cites this paper
• Sequence to Sequence Learning with Neural Networks

  2014cites this paper
• Improving Japanese-English Patent Claim Translation with Clause Segmentation Models based on Word Alignment

  year unknowncites this paper
• Edinburgh Research Explorer A Comparative Quality Evaluation of PBSMT and NMT using Professional Translators

  year unknowninfluential citation