关键词: 动词, 介词, 兼类词, 识别, 规则, 机器翻译

Abstract: Multi-category words are widely distributed in Chinese patent documents. A rule-based method is presented to identify verb and preposition multi-category words in Chinese-English patent machine translation. Based on the principles of boundary perception, and grammatical and semantic information of multi-category words, as well as the context information, serials of disambiguation and identification strategies are designed, which are described in formal rules. Related experiments show the method is efficient to identify verb and preposition multi-category words, and is helpful to improve final translation results.

Key words: verb, preposition, multi-category words, identification, rule, machine translation