A Corpus Level MIRA Tuning Strategy for Machine Translation

MIRA based tuning methods have been widely used in statistical machine translation (SMT) system with a large number of features. Since the corpus-level BLEU is not decomposable, these MIRA approaches usually define a variety of heuristic-driven sentencelevel BLEUs in their model losses. Instead, we present a new MIRA method, which employs an exact corpus-level BLEU to compute the model loss. Our method is simpler in implementation. Experiments on Chinese-toEnglish translation show its effectiveness over two state-of-the-art MIRA implementations.

• Publication year

  2013

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  2013-10-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/d13-1083
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Batch Tuning Strategies for Statistical Machine Translation

  2012influential reference
• Optimization Strategies for Online Large-Margin Learning in Machine Translation

  2012cited by this paper
• Hope and Fear for Discriminative Training of Statistical Translation Models

  2012influential reference
• Optimized Online Rank Learning for Machine Translation

  2012cited by this paper
• SampleRank Training for Phrase-Based Machine Translation

  2011cited by this paper
• 11,001 New Features for Statistical Machine Translation

  2009cited by this paper
• Monte Carlo inference and maximization for phrase-based translation

  2009cited by this paper
• Online Large-Margin Training of Syntactic and Structural Translation Features

  2008influential reference
• Hierarchical Phrase-Based Translation

  2007cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• Online Large-Margin Training for Statistical Machine Translation

  2007cited by this paper
• An End-to-End Discriminative Approach to Machine Translation

  2006cited by this paper
• ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation

  2004cited by this paper
• Support vector machine learning for interdependent and structured output spaces

  2004influential reference
• Online Passive-Aggressive Algorithms

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

  2003influential reference
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Discriminative Training and Maximum Entropy Models for Statistical Machine Translation

  2002cited by this paper
• Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines

  1998cited by this paper

• A simple discriminative training method for machine translation with large-scale features

  2019cites this paper
• Preference learning for machine translation

  2018cites this paper
• Optimization for Statistical Machine Translation: A Survey

  2016cites this paper
• Learning to Rank Algorithms and Their Application in Machine Translation

  2015influential citation
• Une méthode discriminant formation simple pour la traduction automatique avec Grands Caractéristiques

  2015cites this paper
• Improved Online Learning and Modeling for Feature-Rich Discriminative Machine Translation

  2013cites this paper
• Semi-supervised Discriminative Structured Prediction

  2013cites this paper
• A Large Scale Distributed Syntactic, Semantic and Lexical Language Model for Machine Translation

  2011cites this paper