Title | ||
---|---|---|
A comparative study of target dependency structures for statistical machine translation |
Abstract | ||
---|---|---|
This paper presents a comparative study of target dependency structures yielded by several state-of-the-art linguistic parsers. Our approach is to measure the impact of these non-isomorphic dependency structures to be used for string-to-dependency translation. Besides using traditional dependency parsers, we also use the dependency structures transformed from PCFG trees and predicate-argument structures (PASs) which are generated by an HPSG parser and a CCG parser. The experiments on Chinese-to-English translation show that the HPSG parser's PASs achieved the best dependency and translation accuracies. |
Year | Venue | Keywords |
---|---|---|
2012 | ACL | chinese-to-english translation show,statistical machine translation,comparative study,translation accuracy,traditional dependency parsers,dependency structure,hpsg parser,non-isomorphic dependency structure,best dependency,ccg parser,target dependency structure,string-to-dependency translation |
Field | DocType | Volume |
Head-driven phrase structure grammar,LR parser,Computer science,Machine translation,Speech recognition,Artificial intelligence,Natural language processing,Parsing | Conference | P12-2 |
Citations | PageRank | References |
1 | 0.37 | 15 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xianchao Wu | 1 | 64 | 6.62 |
Katsuhito Sudoh | 2 | 326 | 34.44 |
Kevin Duh | 3 | 819 | 72.94 |
Hajime Tsukada | 4 | 449 | 29.46 |
Masaaki Nagata | 5 | 573 | 77.86 |