Long Time No See: Overt Semantics for Machine Translation

In this paper, we show how a computational semantic approach is best fitted to address the translation of highly isolating languages. We use Chinese as an example and present the overall process of translation from Chinese to English, within the framework of Knowledge-Based Machine Translation (KBMT), using an overt semantics while de-emphasizing syntax. We focus here on two particular tasks: Word Sense Disambiguation (WSD) and compound translation.