Name
Title | ||
|---|---|---|
Rule Refinement for Spoken Language Translation by Retrieving the Missing Translation of Content Words |
Abstract | ||
|---|---|---|
Spoken language translation usually suffers from the missing translation of content words, failing to generate the appropriate translation. In this paper we propose a novel Mutual Information based method to improve spoken language translation by retrieving the missing translation of content words. We exploit several features that indicate how well the inner content words are translated for each rule to let MT systems select better translation rules. Experimental results show that our method can improve translation performance significantly ranging from 1.95 to 4.47 BLEU points on different test sets. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/IALP.2013.23 | IALP |
Keywords | Field | DocType |
inner content word,mutual information,missing translation ofcontent word,rule refinement,content word,missing-content word translation retrieval,bleu points,content words,word processing,mutual information-based method,information retrieval,appropriate translation,missing translation,spokenlanguage translation,mt systems,language translation,inner content word translation,translation rule selection,spoken language translation performance improvement,translation performance improvement,spoken language translation,translation performance,natural language processing,bleu point,better translation rule | Rule-based machine translation,Example-based machine translation,Language translation,Computer science,Machine translation,Speech recognition,Machine translation software usability,Transfer-based machine translation,Natural language processing,Artificial intelligence,Computer-assisted translation,Dynamic and formal equivalence | Conference |
Citations | PageRank | References |
0 | 0.34 | 14 |
Authors | ||
5 | ||