Abstract | ||
---|---|---|
In this paper we focus on the incremental decoding for a statistical phrase-based machine translation system. In incremental decoding, translations are generated incrementally for every word typed by a user, instead of waiting for the entire sentence as input. We introduce a novel modification to the beam-search decoding algorithm for phrase-based MT to address this issue, aimed at efficient computation of future costs and avoiding search errors. Our objective is to do a faster translation during incremental decoding without significant reduction in the translation quality. |
Year | Venue | Keywords |
---|---|---|
2010 | WMT@ACL | translation quality,statistical phrase-based machine translation,novel modification,future cost,entire sentence,incremental decoding,phrase-based mt,faster translation,beam-search decoding algorithm,efficient computation,phrase-based statistical machine translation |
Field | DocType | Citations |
Rule-based machine translation,Example-based machine translation,Computer science,Machine translation,Phrase,Speech recognition,Artificial intelligence,Natural language processing,Transfer-based machine translation,Decoding methods,Sentence,Computation | Conference | 8 |
PageRank | References | Authors |
0.64 | 11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Baskaran Sankaran | 1 | 155 | 13.65 |
Ajeet Grewal | 2 | 8 | 0.64 |
Anoop Sarkar | 3 | 1017 | 88.82 |