A new approach to handle unknown words in machine translation is presented. The basic idea is to find definitions for the unknown words on the source language side and translate t...
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 ...
Chinese abbreviations are widely used in modern Chinese texts. Compared with English abbreviations (which are mostly acronyms and truncations), the formation of Chinese abbreviati...
This paper reports on the participation of ITC-irst in the Cross Language Evaluation Forum 2003; in particular, in the monolingual, bilingual, small multilingual, and spoken docum...
In statistical machine translation, the currently best performing systems are based in some way on phrases or word groups. We describe the baseline phrase-based translation system...