Title | ||
---|---|---|
Divide and translate: improving long distance reordering in statistical machine translation |
Abstract | ||
---|---|---|
This paper proposes a novel method for long distance, clause-level reordering in statistical machine translation (SMT). The proposed method separately translates clauses in the source sentence and reconstructs the target sentence using the clause translations with non-terminals. The non-terminals are placeholders of embedded clauses, by which we reduce complicated clause-level reordering into simple word-level reordering. Its translation model is trained using a bilingual corpus with clause-level alignment, which can be automatically annotated by our alignment algorithm with a syntactic parser in the source language. We achieved significant improvements of 1.4% in BLEU and 1.3% in TER by using Moses, and 2.2% in BLEU and 3.5% in TER by using our hierarchical phrase-based SMT, for the English-to-Japanese translation of research paper abstracts in the medical domain. |
Year | Venue | Keywords |
---|---|---|
2010 | WMT@ACL | statistical machine translation,english-to-japanese translation,novel method,clause translation,clause-level reordering,translation model,simple word-level reordering,long distance reordering,hierarchical phrase-based smt,clause-level alignment,alignment algorithm |
Field | DocType | Citations |
Rule-based machine translation,Example-based machine translation,Computer science,Evaluation of machine translation,Machine translation,Phrase,Speech recognition,Machine translation software usability,Natural language processing,Transfer-based machine translation,Artificial intelligence,Sentence | Conference | 15 |
PageRank | References | Authors |
0.81 | 25 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Katsuhito Sudoh | 1 | 326 | 34.44 |
Kevin Duh | 2 | 819 | 72.94 |
Hajime Tsukada | 3 | 449 | 29.46 |
Tsutomu Hirao | 4 | 394 | 31.80 |
Masaaki Nagata | 5 | 573 | 77.86 |