Phrase alignment based on bilingual parsing.
Akira Ushioda · 2007
A novel approach is presented for extracting syntacti-cally motivated phrase alignments. In this method we can incorporate conventional resources such as diction-aries and grammar rules into a statistical optimization framework for phrase alignment. The method extracts bilingual phrases by incrementally merging adjacent words or phrases on both source and target language side in accordance with a global statistical metric. The extracted phrases achieve a maximum F-measure of over 80 with respect to human judged phrase align-ments. The extracted phrases used as training corpus for a phrase-based SMT shows better cross-domain portability over conventional SMT framework.