Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation

Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora show that we can achieve promising results against a competitive baseline by removing the need of specific feature engineering or additional external resources. To justify the utility of our approach, we extract sentence pairs from Wikipedia articles to train machine translation systems and show significant improvements in translation performance.

• Publication year

  2018

• Venue

  International Conference on Computational Linguistics

• Publication date

  2018-06-13

• Fields of study

  Mathematics, Linguistics, Computer Science

• Identifiers
  arXiv 1806.05559
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• MINE: Mutual Information Neural Estimation

  2018cited by this paper
• Bilingual Word Embeddings with Bucketed CNN for Parallel Sentence Extraction

  2017cited by this paper
• Offline bilingual word vectors, orthogonal transformations and the inverted softmax

  2017cited by this paper
• Weighted Set-Theoretic Alignment of Comparable Sentences

  2017cited by this paper
• An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification

  2017cited by this paper
• Word Translation Without Parallel Data

  2017cited by this paper
• Unsupervised Neural Machine Translation

  2017cited by this paper
• OpenNMT: Open-Source Toolkit for Neural Machine Translation

  2017cited by this paper
• TensorFlow: A system for large-scale machine learning

  2016cited by this paper
• Parallel Sentence Extraction from Comparable Corpora with Neural Network Features

  2016cited by this paper
• Dual Learning for Machine Translation

  2016cited by this paper
• Teaching Machines to Read and Comprehend

  2015cited by this paper
• Bilingual Word Representations with Monolingual Quality in Mind

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

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Recurrent Neural Network Regularization

  2014influential reference
• Neural Machine Translation by Jointly Learning to Align and Translate

  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
• On the difficulty of training recurrent neural networks

  2012cited by this paper
• KenLM: Faster and Smaller Language Model Queries

  2011cited by this paper
• Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment

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

  2009cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007influential reference
• Finding Similar Sentences across Multiple Languages in Wikipedia

  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
• Statistical Phrase-Based Translation

  2003cited by this paper
• A Systematic Comparison of Various Statistical Alignment Models

  2003cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Long Short-Term Memory

  1997influential reference
• HMM-Based Word Alignment in Statistical Translation

  1996cited by this paper
• The Mathematics of Statistical Machine Translation: Parameter Estimation

  1993cited by this paper
• Signature Verification Using A "Siamese" Time Delay Neural Network

  1993cited by this paper

• Designing AI-powered translation education tools: a framework for parallel sentence generation using SauLTC and LLMs

  2025cites this paper
• Esposito: An English-Persian Scientific Parallel Corpus for Machine Translation

  2024cites this paper
• Chinese-Vietnamese Pseudo-Parallel Sentences Extraction Based on Image Information Fusion

  2023cites this paper
• Machine Learning-Based Komering Language Translation Engine with Bidirectional RNN Model Algorithm

  2023cites this paper
• KC4MT: A High-Quality Corpus for Multilingual Machine Translation

  2022cites this paper
• Obtaining Parallel Sentences in Low-Resource Language Pairs with Minimal Supervision

  2022cites this paper
• Multi-task learning in under-resourced Dravidian languages

  2022cites this paper
• Unsupervised Parallel Sentences of Machine Translation for Asian Language Pairs

  2022cites this paper
• A Deep Two-State Gated Recurrent Unit for Particulate Matter (PM2.5) Concentration Forecasting

  2022cites this paper
• Expand-Extract: A Parallel Corpus Mining Framework from Comparable Corpora for English-Myanmar Machine Translation

  2022cites this paper
• Refining an Almost Clean Translation Memory Helps Machine Translation

  2022influential citation
• Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

  2021cites this paper
• Similarity Computing Method of Poly-Encoders Short Texts in Both Chinese and Lao Based on Part of Speech Characteristics

  2021cites this paper
• KC4Align: Improving Sentence Alignment method for Low-resource Language Pairs

  2021cites this paper
• Construct-Extract: An Effective Model for Building Bilingual Corpus to Improve English-Myanmar Machine Translation

  2021cites this paper
• Paraphrastic Representations at Scale

  2021cites this paper
• Benchmarking Multi-Task Learning for Sentiment Analysis and Offensive Language Identification in Under-Resourced Dravidian Languages

  2021cites this paper
• Filtering Noisy Parallel Corpus using Transformers with Proxy Task Learning

  2020cites this paper
• Bilingual Text Extraction as Reading Comprehension

  2020influential citation
• A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks

  2020cites this paper
• The Acquisition of Khmer-Chinese Parallel Sentence Pairs From Comparable Corpus Based on Manhattan-BiGRU Model

  2020cites this paper
• Building an Italian-Chinese Parallel Corpus for Machine Translation from the Web

  2020cites this paper
• Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation

  2020cites this paper
• Unsupervised Bitext Mining and Translation via Self-Trained Contextual Embeddings

  2020cites this paper
• 基于跨语言双语预训练及Bi-LSTM的汉-越平行句对抽取方法(Chinese-Vietnamese Parallel Sentence Pair Extraction Method Based on Cross-lingual Bilingual Pre-training and Bi-LSTM)

  2020cites this paper
• SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP

  2020cites this paper
• Human or Neural Translation?

  2020cites this paper
• Parallel Data Extraction using Word Embeddings

  2020cites this paper
• Deep Learning for Text Style Transfer: A Survey

  2020cites this paper
• Chemical-protein Interaction Extraction via ChemicalBERT and Attention Guided Graph Convolutional Networks in Parallel

  2020cites this paper
• Highly Parallel Texts Enriched with Highly Useful Metadata? A Wikipedia Case-Study Combining Machine Learning and Social Technology

  2020cites this paper
• Construction d’un corpus parallèle à partir de corpus comparables pour la simplification de textes médicaux en français [Building a parallel corpus from comparable corpora for French biomedical text simplification]

  2020cites this paper
• Target Sentence Maxpooling Source Sentence Encoder Comparative Translation Loss Language Modeling Loss Encoder Comparative Translation Loss

  2019cites this paper
• Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation

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

  2019cites this paper
• Self-Induced Curriculum Learning in Neural Machine Translation

  2019cites this paper
• Simple and Effective Paraphrastic Similarity from Parallel Translations

  2019cites this paper
• The TransBank Aligner: Cross-Sentence Alignment with Deep Neural Networks

  2019cites this paper
• Online Parallel Data Extraction with Neural Machine Translation

  2019influential citation
• Large-scale Hierarchical Alignment for Author Style Transfer

  2018cites this paper
• Large-Scale Hierarchical Alignment for Data-driven Text Rewriting

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

  2018cites this paper
• Computer Science & Information Technology

  2018cites this paper