Abstract
We present a new translation model that include undecorated hierarchical-style phrase rules, decorated source-syntax rules, and partially decorated rules.
Results show an increase in translation performance of up to 0.8% BLEU for German--English translation when trained on the news-commentary corpus, using syntactic annotation from a source language parser. We also experimented with annotation from shallow taggers and found this increased performance by 0.5% BLEU.
Results show an increase in translation performance of up to 0.8% BLEU for German--English translation when trained on the news-commentary corpus, using syntactic annotation from a source language parser. We also experimented with annotation from shallow taggers and found this increased performance by 0.5% BLEU.
Original language | English |
---|---|
Title of host publication | Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR |
Place of Publication | Stroudsburg, PA, USA |
Publisher | Association for Computational Linguistics |
Pages | 409-417 |
Number of pages | 9 |
Publication status | Published - 2010 |