Abstract | ||
---|---|---|
This paper presents a method to improve the translation of polysemous nouns, when a previous occurrence of the noun as the head of a compound noun phrase is available in a text. The occurrences are identified through pattern matching rules, which detect XY compounds followed closely by a potentially coreferent occurrence of Y, such as "Nordwand ... Wand". Two strategies are proposed to improve the translation of the second occurrence of Y: re-using the cached translation of Y from the XY compound, or post-editing the translation of Y using the head of the translation of XY. Experiments are performed on Chinese-to-English and German-to-French statistical machine translation, over the WIT3 and Text+Berg corpora respectively, with 261 XY/Y pairs each. The results suggest that while the overall BLEU scores increase only slightly, the translations of the targeted polysemous nouns are significantly improved. |
Year | Venue | Field |
---|---|---|
2015 | 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING: PROCEEDINGS OF THE STUDENT RESEARCH WORKSHOP (ACL-IJCNLP 2015) | Noun phrase,Rule-based machine translation,Example-based machine translation,BLEU,Computer science,Machine translation,Noun,Speech recognition,Artificial intelligence,Natural language processing,Pattern matching,German |
DocType | Volume | Citations |
Conference | P15-3 | 2 |
PageRank | References | Authors |
0.43 | 10 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiao Pu | 1 | 3 | 1.45 |
Laura Mascarell | 2 | 7 | 2.61 |
Andrei Popescu-Belis | 3 | 573 | 64.13 |
Mark Fishel | 4 | 64 | 17.32 |
Ngoc-Quang Luong | 5 | 43 | 8.43 |
Martin Volk | 6 | 47 | 11.21 |