Abstract | ||
---|---|---|
We describe MSR-MT, a large-scale hybrid machine translation system under development for several language pairs. This system's ability to acquire its primary translation knowledge automatically by parsing a bilingual corpus of hundreds of thousands of sentence pairs and aligning resulting logical forms demonstrates true promise for overcoming the so-called MT customization bottleneck. Trained on English and Spanish technical prose, a blind evaluation shows that MSR-MT's integration of rule-based parsers, example based processing, and statistical techniques produces translations whose quality exceeds that of uncustomized commercial MT systems in this domain. |
Year | DOI | Venue |
---|---|---|
2001 | 10.3115/1118037.1118039 | DDMMT@ACL |
Keywords | Field | DocType |
logical form,uncustomized commercial mt system,bilingual corpus,primary translation knowledge,large-scale hybrid machine translation,example-based mt,rule-based parsers,language pair,blind evaluation,so-called mt customization bottleneck,spanish technical prose,rule based,machine translation | Example-based machine translation,Bottleneck,Computer science,Natural language processing,Artificial intelligence,Transfer-based machine translation,Hybrid machine translation,Parsing,Sentence,Personalization | Conference |
Volume | Citations | PageRank |
W01-14 | 24 | 3.41 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stephen D. Richardson | 1 | 282 | 39.22 |
Bill Dolan | 2 | 2137 | 132.21 |
Arul Menezes | 3 | 470 | 29.57 |
Monica Corston-Oliver | 4 | 32 | 5.13 |