关键词: 基于语料库的翻译研究, 三元组可比语料库, 自动语言剖析, n元词串

Abstract: At present, the Corpus-Based Translation Studies（CBTS） at home and abroad mainly focus on the studies of translation universals, translation norms, translator’s style and translation training, which involve studies in both translation theory and practice. The research and application of the automatic language profiling technologies proposed in this paper expand CBTS’s scientific connotation to include the NLP-oriented research and application. Based on the consideration of project feasibility, this paper puts forward the building of 3-tuple comparable corpora and apply the automatic extracting technologies like n-grams, key clusters and semantic multi-word expressions to exploit the English native language models, so as to achieve improvement and further development of natural language processing applications such as machine translation and cross-language information retrieval.

Key words: Corpus-Based Translation Studies（CBTS）, 3-tuple comparable corpora, automatic language profiling, n-grams