Abstract | ||
---|---|---|
We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation. This method requires a source-language dependency parser, target language word segmentation and an unsupervised word alignment component. We align a parallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model. We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser. |
Year | DOI | Venue |
---|---|---|
2005 | 10.3115/1219840.1219874 | ACL |
Keywords | Field | DocType |
novel approach,statistical machine translation,phrasal smt,phrasal translation,source language,source-language dependency parser,dependency treelet translation pair,source dependency parse,promising approach,conventional smt model,word segmentation,dependency parsing | Rule-based machine translation,Example-based machine translation,Computer science,Machine translation,Text segmentation,Dependency grammar,Speech recognition,Artificial intelligence,Natural language processing,Parsing,Syntax,Sentence | Conference |
Volume | Citations | PageRank |
P05-1 | 211 | 8.90 |
References | Authors | |
33 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chris Quirk | 1 | 1362 | 77.61 |
Arul Menezes | 2 | 470 | 29.57 |
Colin Cherry | 3 | 1257 | 66.49 |