Paper Info
Title
n-best reranking for the efficient integration of word sense disambiguation and statistical machine translation
Abstract
Although it has been always thought that Word Sense Disambiguation (WSD) can be useful for Machine Translation, only recently efforts have been made towards integrating both tasks to prove that this assumption is valid, particularly for Statistical Machine Translation (SMT). While different approaches have been proposed and results started to converge in a positive way, it is not clear yet how these applications should be integrated to allow the strengths of both to be exploited. This paper aims to contribute to the recent investigation on the usefulness of WSD for SMT by using n-best reranking to efficiently integrate WSD with SMT. This allows using rich contextual WSD features, which is otherwise not done in current SMT systems. Experiments with English-Portuguese translation in a syntactically motivated phrase-based SMT system and both symbolic and probabilistic WSD models showed significant improvements in BLEU scores.
Year
DOI
Venue
2008
10.1007/978-3-540-78135-6_34
CICLing
Keywords
Field
DocType
word sense disambiguation,n-best reranking,bleu score,statistical machine translation,probabilistic wsd model,machine translation,rich contextual wsd feature,english-portuguese translation,smt system,different approach,efficient integration,current smt system,word sense
Inductive logic programming,Example-based machine translation,Computer science,Machine translation,Phrase,Speech recognition,Machine translation software usability,Natural language processing,Artificial intelligence,Transfer-based machine translation,Probabilistic logic,Word-sense disambiguation
Conference
Volume
ISSN
ISBN
4919
0302-9743
3-540-78134-X
Citations 
PageRank 
References 
9
0.52
14
Authors
3
Name
Order
Citations
PageRank
lucia specia11217122.84
Baskaran Sankaran215513.65
Maria das Graças Volpe Nunes332734.20