Research On Chinese Translation Of English Verbs In English-Chinese Machine Translation

Machine translation has always been a dream of mankind, which is an arduous and complicated task. Its difficulty mainly lies in the complexity of language knowledge and our limited understanding of the rules of human languages. Verbs are the core of the sentence, which determine the sentence structure, and occupy a dominant position in the sentence. Furthermore, verbs are the most active parts of languages, which vary much with complex forms and multi-meanings. Translation of verbs, which is urgently needed to be resolved, has a critical influence on the quality of translation of the entire sentence. Researchers have studied verbs from different fields. However, disambiguation and translation of verbs is still one of the difficulties in the field of machine translation.Prof. Qingshi Gao proposed the semantic language theory and multi-language machine translation approach based on semantic language in 2003.In this paper, the concept of verb semantic patterns was proposed based on the semantic language theory. Verbs were studied based on semantic patterns. The rules of combination of semantics were described with semantic patterns. The extraction method for semantic patterns was introduced, and semantic patterns were extracted from a large number of corpus.Three verb semantic patterns were concluded, including V semantic pattern, contiguous VO semantic pattern and non-contiguous VO semantic pattern. The structure and construction method of semantic pattern base were described. The semantic pattern base, fixed pattern base and variable base were constructed with commonly used verbs as research objects.Based on such bases, a new Chinese translation algorithm of verbs was proposed for semantic analysis and Chinese translation of English verbs.In this paper, a Chinese translation algorithm of verbs was proposed based on semantic pattern base, fixed pattern base and variable base.40,000 sentence pairs from bilingual corpus in Xiamen University were selected for open test. The test results demonstrate that this method could resolve the semantic analysis and Chinese translation of English verbs effectively.