Title :
Rule Refinement for Spoken Language Translation by Retrieving the Missing Translation of Content Words
Author :
Linfeng Song ; Jun Xie ; Xing Wang ; Yajuan Lu ; Qun Liu
Author_Institution :
Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, Chile
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.
Keywords :
information retrieval; language translation; natural language processing; word processing; BLEU points; MT systems; inner content word translation; missing-content word translation retrieval; mutual information-based method; rule refinement; spoken language translation performance improvement; translation performance improvement; translation rule selection; Data models; Educational institutions; Heuristic algorithms; Mutual information; Pragmatics; Training; Training data; Content Words; Mutual Information; Rule Refinement; Spoken Language Translation;
Conference_Titel :
Asian Language Processing (IALP), 2013 International Conference on
Conference_Location :
Urumqi
DOI :
10.1109/IALP.2013.23