Improving Statistical Machine Translation using Lexicalized Rule Selection

This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine rich context information for selecting translation rules during decoding. We successfully integrate the MaxEnt-based rule selection models into the state-of-the-art syntax-based SMT model. Experiments show that our lexicalized approach for rule selection achieves statistically significant improvements over the state-of-the-art SMT system.

• Publication year

  2008

• Venue

  International Conference on Computational Linguistics

• Publication date

  2008-08-18

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1599081.1599122
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Word Sense Disambiguation Improves Statistical Machine Translation

  2007cited by this paper
• Improving Statistical Machine Translation Using Word Sense Disambiguation

  2007influential reference
• Hierarchical Phrase-Based Translation

  2007influential reference
• How phrase sense disambiguation outperforms word sense disambiguation for statistical machine translation

  2007influential reference
• Statistical Syntax-Directed Translation with Extended Domain of Locality

  2006cited by this paper
• Discriminative Reordering Models for Statistical Machine Translation

  2006cited by this paper
• Scalable Inference and Training of Context-Rich Syntactic Translation Models

  2006cited by this paper
• Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation

  2006cited by this paper
• Tree-to-String Alignment Template for Statistical Machine Translation

  2006cited by this paper
• A Hierarchical Phrase-Based Model for Statistical Machine Translation

  2005influential reference
• Better k-best Parsing

  2005cited by this paper
• Pharaoh: a beam search decoder for phrase-based statistical machine translation models

  2004cited by this paper
• Maximum Entropy Modeling Toolkit for Python and C

  2004cited by this paper
• Interpreting BLEU/NIST Scores: How Much Improvement do We Need to Have a Better System?

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

  2004cited by this paper
• Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models

  2004cited by this paper
• Statistical Phrase-Based Translation

  2003cited by this paper
• Minimum Error Rate Training in Statistical Machine Translation

  2003cited by this paper
• Discriminative Training and Maximum Entropy Models for Statistical Machine Translation

  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
• Improved Statistical Alignment Models

  2000cited by this paper
• A Maximum Entropy Approach to Natural Language Processing

  1996cited by this paper

• A neural machine translation method based on split graph convolutional self-attention encoding

  2024cites this paper
• Dual contextual module for neural machine translation

  2021cites this paper
• Fˆ2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax

  2020cites this paper
• Integrating Shallow Syntactic Labels in the Phrase-Boundary Translation Model

  2018cites this paper
• Modeling Indicative Context for Statistical Machine Translation

  2017cites this paper
• A Continuous Space Rule Selection Model for Syntax-based Statistical Machine Translation

  2016cites this paper
• Improving Phrase-Based SMT Using Cross-Granularity Embedding Similarity

  2016cites this paper
• Learning local word reorderings for hierarchical phrase-based statistical machine translation

  2016cites this paper
• Learning from User Feedback for Machine Translation in Real-Time

  2016cites this paper
• A Framework for Discriminative Rule Selection in Hierarchical Moses

  2016influential citation
• Phrase-boundary model for statistical machine translation

  2016cites this paper
• Dependency graph-based statistical machine translation

  2016cites this paper
• Context-Dependent Translation Selection Using Convolutional Neural Network

  2015cites this paper
• Graph-Based Collective Lexical Selection for Statistical Machine Translation

  2015influential citation
• Learning Word Reorderings for Hierarchical Phrase-based Statistical Machine Translation

  2015cites this paper
• Dynamic Topic Adaptation for Improved Contextual Modelling in Statistical Machine Translation

  2015cites this paper
• Decoding strategies for syntax-based statistical machine translation

  2015cites this paper
• Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation

  2015cites this paper
• A Context-Aware Topic Model for Statistical Machine Translation

  2015cites this paper
• Learning Topic Representation for SMT with Neural Networks

  2014cites this paper
• Type-Driven Incremental Semantic Parsing with Polymorphism

  2014cites this paper
• Topic-aware pivot language approach for statisticalmachine translation

  2014cites this paper
• The DCU-ICTCAS MT system at WMT 2014 on German-English Translation Task

  2014cites this paper
• A Lexicalized Reordering Model for Hierarchical Phrase-based Translation

  2014cites this paper
• Topic-Based Dissimilarity and Sensitivity Models for Translation Rule Selection

  2014cites this paper
• Case Frame Constraints for Hierarchical Phrase-Based Translation: Japanese-Chinese as an Example

  2014cites this paper
• Soft Dependency Matching for Hierarchical Phrase-based Machine Translation

  2014cites this paper
• Stem Translation with Affix-Based Rule Selection for Agglutinative Languages

  2013cites this paper
• Handling Ambiguities of Bilingual Predicate-Argument Structures for Statistical Machine Translation

  2013cites this paper
• Max-Violation Perceptron and Forced Decoding for Scalable MT Training

  2013cites this paper
• The application of source language information in Chinese-English statistical machine translation

  2013cites this paper
• TRANSLATING LEGAL SENTENCE BY SEGMENTATION AND RULE SELECTION

  2013cites this paper
• A Topic Similarity Model for Hierarchical Phrase-based Translation

  2012cites this paper
• Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information

  2012cites this paper
• Archives des publications du CNRC ( NPArC ) Bilingual Sense Similarity for Statistical Machine Translation

  2011cites this paper
• An Orientation Model for Hierarchical Phrase-Based Translation

  2011cites this paper
• Incorporating Translation Quality-Oriented Features into Log-Linear Models of Machine Translation

  2011cites this paper
• A Unified and Discriminative Soft Syntactic Constraint Model for Hierarchical Phrase-based Translation

  2011influential citation
• Using Rich Linguistic and Contextual Information for Tree-Based Statistical Machine Translation

  2011cites this paper
• Integrating Source-Language Context into Log-Linear Models of Statistical Machine Translation

  2011cites this paper
• Better Filtration and Augmentation for Hierarchical Phrase-Based Translation Rules

  2010influential citation
• Maximum Entropy Based Phrase Reordering for Hierarchical Phrase-Based Translation

  2010cites this paper
• Bilingual Sense Similarity for Statistical Machine Translation

  2010cites this paper
• Statistical Translation Model Based On Source Syntax Structure

  2010cites this paper
• Structured local exponential models for machine translation

  2010cites this paper
• A Joint Rule Selection Model for Hierarchical Phrase-Based Translation

  2010cites this paper
• Supertags as Source Language Context in Hierarchical Phrase-Based SMT

  2010influential citation
• Lexical Features for Statistical Machine Translation

  2009cites this paper
• Using Supertags as Source Language Context in SMT

  2009cites this paper
• Effective Use of Linguistic and Contextual Information for Statistical Machine Translation

  2009influential citation
• Title of dissertation : LEXICAL FEATURES FOR STATISTICAL MACHINE TRANSLATION

  2009cites this paper
• Maximum Entropy based Rule Selection Model for Syntax-based Statistical Machine Translation

  2008cites this paper
• The Maximum Entropy based Rule Selection Model for Statistical Machine Translation (Invited Paper)

  2008cites this paper