Graph-based Learning for Statistical Machine Translation

Current phrase-based statistical machine translation systems process each test sentence in isolation and do not enforce global consistency constraints, even though the test data is often internally consistent with respect to topic or style. We propose a new consistency model for machine translation in the form of a graph-based semi-supervised learning algorithm that exploits similarities between training and test data and also similarities between different test sentences. The algorithm learns a regression function jointly over training and test data and uses the resulting scores to rerank translation hypotheses. Evaluation on two travel expression translation tasks demonstrates improvements of up to 2.6 BLEU points absolute and 2.8% in PER.

• Publication year

  2009

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2009-05-31

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1620754.1620772
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• Kernel Regression Based Machine Translation

  2007cited by this paper
• Transductive learning for statistical machine translation

  2007cited by this paper
• Data-Driven Graph Construction for Semi-Supervised Graph-Based Learning in NLP

  2007cited by this paper
• Seeing stars when there aren’t many stars: Graph-based semi-supervised learning for sentiment categorization

  2006cited by this paper
• Maximum Margin Semi-Supervised Learning for Structured Variables

  2005cited by this paper
• Semi-supervised learning with graphs

  2005influential reference
• Word Sense Disambiguation Using Label Propagation Based Semi-Supervised Learning

  2005cited by this paper
• Efficient Computation of Gapped Substring Kernels on Large Alphabets

  2005cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005cited by this paper
• Efficient computation of gap-weighted string kernels on large alphabets

  2004cited by this paper
• Transductive Learning via Spectral Graph Partitioning

  2003cited by this paper
• Text Classification using String Kernels

  2002cited by this paper
• SRILM - an extensible language modeling toolkit

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

  2002cited by this paper
• Learning from labeled and unlabeled data with label propagation

  2002cited by this paper
• Text classification using string kernels

  2002cited by this paper
• Towards a Unified Approach to Memory- and Statistical-Based Machine Translation

  2001cited by this paper
• Partially labeled classification with Markov random walks

  2001cited by this paper
• Learning from Labeled and Unlabeled Data using Graph Mincuts

  2001cited by this paper
• Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger

  2000cited by this paper
• A new parallel matrix multiplication algorithm on distributed-memory concurrent computers

  1997cited by this paper
• Tree cover search algorithm for example-based translation

  1992cited by this paper

• Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis

  2019cites this paper
• Varia Discourse in Statistical Machine Translation A Survey and a Case Study

  2018influential citation
• Information Extraction from Scientific Literature for Method Recommendation

  2018cites this paper
• GraphNER: Using Corpus Level Similarities and Graph Propagation for Named Entity Recognition

  2018cites this paper
• State-of-the-Art in UVs’ Autonomous Motion Planning

  2018cites this paper
• Word Sense Consistency in Statistical and Neural Machine Translation

  2018cites this paper
• Explorer Unsupervised Semantic Role Induction with Graph Partitioning

  2017cites this paper
• A Model Literature Analysis on Machine Translation System Finding Research Problem in English to Hindi Translation Systems

  2017cites this paper
• Deep Submodular Functions

  2017cites this paper
• Acoustic classification using semi-supervised Deep Neural Networks and stochastic entropy-regularization over nearest-neighbor graphs

  2017cites this paper
• Autonomous Reactive Mission Scheduling and Task-Path Planning Architecture for Autonomous Underwater Vehicle

  2017cites this paper
• Graph-based Semi-supervised Gene Mention Tagging

  2016cites this paper
• Semi-Supervised Phone Classification using Deep Neural Networks and Stochastic Graph-Based Entropic Regularization

  2016cites this paper
• Leveraging Compounds to Improve Noun Phrase Translation from Chinese and German First

  2015cites this paper
• Paraphrases for Statistical Machine Translation

  2015cites this paper
• Leveraging Compounds to Improve Noun Phrase Translation from Chinese and German

  2015cites this paper
• Improving Statistical Machine Translation with a Multilingual Paraphrase Database

  2015cites this paper
• A survey of graphs in natural language processing*

  2015influential citation
• Optimal route planning with prioritized task scheduling for AUV missions

  2015cites this paper
• L2S: Transforming Natural Language Questions into SQL Queries

  2015cites this paper
• A Graph-based Algorithm to Build Knowledge Map for Minority Languages

  2015cites this paper
• Modelling contextual constraints in probabilistic relaxation for multi-class semi-supervised learning

  2014cites this paper
• Graph-based Semi-Supervised Learning of Translation Models from Monolingual Data

  2014cites this paper
• Graph-Based Semi-Supervised Learning

  2014cites this paper
• Sentiment Classification in Under-Resourced Languages Using Graph-Based Semi-Supervised Learning Methods

  2014cites this paper
• Getting Past the Language Gap: Innovations in Machine Translation

  2013cites this paper
• LEVERAGING DIVERSE SOURCES IN STATISTICAL MACHINE TRANSLATION

  2013cites this paper
• Mutual k-Nearest Neighbor Graph Construction in Graph-based Semi-Supervised Classification

  2013cites this paper
• Graph Propagation for Paraphrasing Out-of-Vocabulary Words in Statistical Machine Translation

  2013cites this paper
• Discourse in Statistical Machine Translation

  2012influential citation
• Learning Translation Consensus with Structured Label Propagation

  2012influential citation
• Pattern Recognition System for Translating the English Sentence into Hindi

  2012cites this paper
• The Trouble with SMT Consistency

  2012cites this paper
• Statistical Mechanical Analysis of Semantic Orientations on Lexical Network

  2012cites this paper
• Scaling Up Machine Learning: Parallel Graph-Based Semi-Supervised Learning

  2011cites this paper
• Using the Mutual k-Nearest Neighbor Graphs for Semi-supervised Classification on Natural Language Data

  2011cites this paper
• Unsupervised Semantic Role Induction with Graph Partitioning

  2011cites this paper
• Automatic Annotation of Spoken Language Using Out-of-Domain Resources and Domain Adaptation

  2011influential citation
• Semi-Supervised Learning with Measure Propagation

  2011cites this paper
• Efficient Graph-Based Semi-Supervised Learning of Structured Tagging Models

  2010cites this paper