Finding Target Language Correspondence for Lexicalized EBMT System

This paper presents a three-phase approach to find the correspondence in Target Language (TL) sentence for a fragment of Source Language (SL) sentence in a lexicalized EBMT system. To be practical, it exploits surface information as much as possible instead of using parsers. Experiments show that, although not so perfect, it is very robust and effective. The three phases are: First, align the sentence pair at word level in order to provide anchors for phrase alignment. Second, based on the aligned anchors, find all the TL fragments which may possibly correspond to a SL fragment. And finally, using a score function, select the best TL fragment as the correspondence of a SL fragment.

• Type: Conference
• Year: 2001
• Where: NLPRS
• Authors: Wei Wang, Jin-Xia Huang, Ming Zhou, Changning Huang
• Keywords: Lexicalized Ebmt System, Natural Language Processing, NLPRS 2001, SL Fragment, Tl Fragment