The University of Maryland Statistical Machine Translation System for the Fourth Workshop on Machine Translation

This paper describes the techniques we explored to improve the translation of news text in the German-English and Hungarian-English tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, and incorporation of a feature scoring the alignment of function words in the hypothesized translation. We also explored the use of monolingual paraphrases to improve coverage, as well as co-training to improve the quality of the segmentation lattices used, but these did not lead to improvements.

• Publication year

  2009

• Venue

  WMT@EACL

• Publication date

  2009-03-30

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1626431.1626461
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Using a maximum entropy model to build segmentation lattices for MT

  2009cited by this paper
• Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices

  2009cited by this paper
• Towards better Machine Translation Quality for the German-English Language Pairs

  2008cited by this paper
• Generalizing Word Lattice Translation

  2008cited by this paper
• Tera-Scale Translation Models via Pattern Matching

  2008cited by this paper
• Refinements in BTG-based Statistical Machine Translation

  2008cited by this paper
• Lattice-based Minimum Error Rate Training for Statistical Machine Translation

  2008influential reference
• Ordering Phrases with Function Words

  2007cited by this paper
• Randomised Language Modelling for Statistical Machine Translation

  2007cited by this paper
• Hierarchical Phrase-Based Translation

  2007cited by this paper
• Forest Rescoring: Faster Decoding with Integrated Language Models

  2007cited by this paper
• Hierarchical Phrase-Based Translation with Suffix Arrays

  2007cited by this paper
• A Study of Translation Edit Rate with Targeted Human Annotation

  2006cited by this paper
• Improved Statistical Machine Translation Using Paraphrases

  2006cited by this paper
• Going Beyond AER: An Extensive Analysis of Word Alignments and Their Impact on MT

  2006cited by this paper
• AcmA of Lactococcus lactis is an N‐acetylglucosaminidase with an optimal number of LysM domains for proper functioning

  2005cited by this paper
• A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION

  2005cited by this paper
• Minimum Bayes-Risk Decoding for Statistical Machine Translation

  2004cited by this paper
• Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources

  2004cited by this paper
• Empirical Methods for Compound Splitting

  2003cited by this paper
• Statistical Phrase-Based Translation

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

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

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

  2002influential reference
• SRILM - an extensible language modeling toolkit

  2002cited by this paper
• Extracting Paraphrases from a Parallel Corpus

  2001cited by this paper
• Automatic Identification of Word Translations from Unrelated English and German Corpora

  1999cited by this paper
• High quality word graphs using forward-backward pruning

  1999cited by this paper
• An Empirical Study of Smoothing Techniques for Language Modeling

  1996cited by this paper
• Improved backing-off for M-gram language modeling

  1995cited by this paper
• Accurate Methods for the Statistics of Surprise and Coincidence

  1993cited by this paper

• Optimization for Statistical Machine Translation: A Survey

  2016cites this paper
• The University of Illinois submission to the WMT 2015 Shared Translation Task

  2015cites this paper
• Multi-Metric Optimization Using Ensemble Tuning

  2013cites this paper
• Improvements in hierarchical phrase-based Statistical Machine Translation

  2013cites this paper
• Why Not Grab a Free Lunch? Mining Large Corpora for Parallel Sentences to Improve Translation Modeling

  2012cites this paper
• Learning to Translate with Multiple Objectives

  2012cites this paper
• Learning to Transform and Select Elementary Trees for Improved Syntax-based Machine Translations

  2011cites this paper
• Noisy SMS Machine Translation in Low-Density Languages

  2011cites this paper
• Metric and reference factors in minimum error rate training

  2010cites this paper
• The University of Maryland Statistical Machine Translation System for the Fifth Workshop on Machine Translation

  2010influential citation
• Language Model and Grammar Extraction Variation in Machine Translation

  2010cites this paper
• Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation

  2010cites this paper
• Compound Processing for Phrase-Based Statistical Machine Translation

  2009cites this paper
• Improving the Objective Function in Minimum Error Rate Training

  2009influential citation
• Findings of the 2009 Workshop on Statistical Machine Translation

  2009cites this paper