Extracting translations from comparable corpora for Cross-Language Information Retrieval using the language modeling framework
作者：
Highlights：
• Proposing a language modeling method to extract translations from comparable corpora.
• Comparing two similarity functions for deriving bilingual word correlations.
• Improving translation quality by integrating co-occurrence relations into word models.
• Comparing different estimations of translation probabilities from word correlations.
• Showing the significant impact of probability estimation methods on CLIR performance.
摘要
•Proposing a language modeling method to extract translations from comparable corpora.•Comparing two similarity functions for deriving bilingual word correlations.•Improving translation quality by integrating co-occurrence relations into word models.•Comparing different estimations of translation probabilities from word correlations.•Showing the significant impact of probability estimation methods on CLIR performance.
论文关键词：Translation model,Bilingual lexicon,Comparable corpora,Cross-Language Information Retrieval,Language modeling framework
论文评审过程：Received 13 November 2014, Revised 10 August 2015, Accepted 17 August 2015, Available online 10 November 2015, Version of Record 19 February 2016.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.08.001
