Improving the Quality of Word Alignment by Integrating Pearson's Chi-Square Test Information
Authors:
- Cuong HoangCHCuong Hoang
- Cuong-Anh LeCLCuong-Anh Le
- Son-Bao PhamSPSon-Bao Pham
- 1 November 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 121-124
Abstract
Previous researches mainly focus on the approaches which are essentially inspirited from the log-linear model background in machine learning or other adaptations. However, not a lot of studies deeply focus on improving word-alignment models to enhance the quality of phrase translation table. This research will follow on that approach. The experiments show that this scheme could also improve the quality of the word-alignment component better. Hence, the improvement impacts the quality of translation system in overall around 1% for the BLEU score metric.Keywords
This publication has 8 references indexed in Scilit:
- Moses2007
- N-gram-based Machine TranslationComputational Linguistics, 2006
- A hierarchical phrase-based model for statistical machine translation2005
- The Alignment Template Approach to Statistical Machine TranslationComputational Linguistics, 2004
- A Systematic Comparison of Various Statistical Alignment ModelsComputational Linguistics, 2003
- Statistical phrase-based translation2003
- Identifying word correspondence in parallel texts1991
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977