Estimating phrase pair relevance for translation model pruning
Abstract:
We present pruning strategies for translation models that are based on estimating the relevance of phrase pairs. We apply the overall translation system to a set of data and collect a number of statistics for each phrase pair. Using these statistics in various scoring terms we are able to significantly outperform baseline pruning methods and we can show that the number of phrase pairs can be reduced by up to 80% without significantly affecting the overall system performance.
| Zugehörige Institution(en) am KIT | Institut für Theoretische Informatik (ITI) |
| Publikationstyp | Buchaufsatz |
| Publikationsjahr | 2007 |
| Sprache | Englisch |
| Identifikator | KITopen-ID: 1000009546 |
| Erschienen in | 11th Machine Translation Summit, organized by the EAMT, Copenhagen, Denmark, September 10-14, 2007. Ed.: B. Maegaard |
| Verlag | European Association for Machine Translation (EAMT) |
| Externe Relationen | Siehe auch Siehe auch |