Translation model pruning via usage statistics for statistical machine translation
Abstract:
We describe a new pruning approach to remove phrase pairs from translation models of statistical machine translation systems. The approach applies the original translation system to a large amount of text and calculates usage statistics for the phrase pairs. Using these statistics the relevance of each phrase pair can be estimated. The approach is tested against a strong baseline based on previous work and shows significant improvements.
| Zugehörige Institution(en) am KIT | Institut für Theoretische Informatik (ITI) |
| Publikationstyp | Proceedingsbeitrag |
| Publikationsjahr | 2007 |
| Sprache | Englisch |
| Identifikator | KITopen-ID: 1000009556 |
| Erschienen in | Human language technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, April 22-27, 2007, Rochester, New York, USA. Hrsg.: C. Sidner |
| Veranstaltung | Annual Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies (NAACL/HLT 2007), Rochester, NY, USA, 22.04.2007 – 27.04.2007 |
| Verlag | ACL |
| Seiten | 21-24 |
| Externe Relationen | Siehe auch |