Word Alignment Based On Bilingual Bracketing
Abstract:
In this paper, an improved word alignment based on bilingual bracketing is described. The explored approaches include using Model-1 conditional probability, a boosting strategy for lexicon probabilities based on importance sampling, applying Parts of Speech to discriminate English words and incorporating information of English base noun phrase. The results of the shared task on French-English, RomanianEnglish and Chinese-English word alignments are presented and discussed.
| Zugehörige Institution(en) am KIT | Institut für Anthropomatik und Robotik (IAR) |
| Publikationstyp | Proceedingsbeitrag |
| Publikationsjahr | 2003 |
| Sprache | Englisch |
| Identifikator | KITopen-ID: 1000166454 |
| Erschienen in | Proceedings of the HLT-NAACL Workshop: Building and Using Parallel Texts Data Driven Machine Translation and Beyond, HLT-NAACL 2003, Edmonton, Canada, 31 May 2003 |
| Veranstaltung | HLT-NAACL Workshop: Building and Using Parallel Texts Data Driven Machine Translation and Beyond (2003), Edmonton, Kanada, 31.05.2003 |
| Verlag | Association for Computational Linguistics (ACL) |
| Seiten | 15-18 |