Abstract | ||
---|---|---|
In the development of a machine translation system, one important issue is being able to adapt to a specific domain without requiring time-consuming lexical work. We have experimented with using a statistical word-alignment algorithm to derive word association pairs (French-English) that complement an existing multi-purpose bilingual dictionary. This word association information is added to the system at the time of the automatic creation of our translation pattern database, thereby making this database more domain specific. This technique significantly improves the overall quality of translation, as measured in an independent blind evaluation. |
Year | DOI | Venue |
---|---|---|
2001 | 10.3115/1118037.1118051 | DDMMT@ACL |
Keywords | Field | DocType |
important issue,specific domain,word association information,mt system,word association pair,automatic creation,existing multi-purpose bilingual dictionary,domain specific,domain specificity,independent blind evaluation,translation pattern database,machine translation system,machine translation | Rule-based machine translation,Bilingual dictionary,Domain specificity,Computer science,Machine translation system,Word error rate,Speech recognition,Artificial intelligence,Transfer-based machine translation,Word Association,Natural language processing | Conference |
Volume | Citations | PageRank |
W01-14 | 6 | 1.26 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jessie Pinkham | 1 | 35 | 5.16 |
Monica Corston-Oliver | 2 | 32 | 5.13 |