Abstract | ||
---|---|---|
In Statistical Machine Translation, reordering rules have proved useful in extracting bilingual phrases and in decoding during translation between languages that are structurally different. Linguistically motivated rules have been incorporated into Chinese-to-English (Wang et al., 2007) and English-to-Japanese (Isozaki et al., 2010b) translation with significant gains to the statistical translation system. Here, we carry out a linguistic analysis of the Chinese-to-Japanese translation problem and propose one of the first reordering rules for this language pair. Experimental results show substantially improvements (from 20.70 to 23.17 BLEU) when head-finalization rules based on HPSG parses are used, and further gains (to 24.14 BLEU) were obtained using more refined rules. |
Year | Venue | Keywords |
---|---|---|
2012 | SSST@ACL | bilingual phrase,linguistically motivated rule,statistical translation system,reordering rule,head-finalization rule,statistical machine translation,chinese-to-japanese translation problem,language pair,head finalization reordering,chinese-to-japanese machine translation,hpsg parses |
Field | DocType | Volume |
Head-driven phrase structure grammar,Rule-based machine translation,Example-based machine translation,Computer science,Evaluation of machine translation,Machine translation,Speech recognition,Machine translation software usability,Artificial intelligence,Transfer-based machine translation,Finalization,Natural language processing | Conference | W12-42 |
Citations | PageRank | References |
6 | 0.77 | 26 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Han Dan | 1 | 12 | 1.87 |
Katsuhito Sudoh | 2 | 326 | 34.44 |
Xianchao Wu | 3 | 64 | 6.62 |
Kevin Duh | 4 | 819 | 72.94 |
Hajime Tsukada | 5 | 449 | 29.46 |
Masaaki Nagata | 6 | 573 | 77.86 |