国内英汉双语平行语料库建构与研究现状及展望

An Overview of the E-C Parallel Corpus-Based Translation Studies in China

本文在回顾近年来国内英汉双语平行语料库建构与研究方面取得成就的基础上,探究现有语料库研制与应用中存在的一些问题,发现其具体表现为:第一,语料库建设各自为政,缺乏超大规模、综合性、多用途的国家级平行语料库;第二,语料库的深加工还不够深入;第三,从对语料库的应用看,课题拓展和对语料库的研究潜力开发还不够;第四,相关学科之间的沟通与合作不够。针对这些问题提出的一些对策包括构建更大规模的超级英汉平行语料库、自动标注的深化、开发相关软件以及完善网络检索平台。

Based on a brief overview of the feats achieved in the field of English-Chinese parallel corpus-based translations in China in recent years , the present paper attempts to point out some problems :( 1 ) lack of large-scale , comprehensive and multi-purpose national parallel corpora resulting from lack of communication between different corpus projects ;( 2 ) lack of in-depth processing in corpora compilation ;( 3 ) under-developed new research topics and potential of the parallel corpus ;( 4 ) lack of communication between related disciplines , such as the one between computational linguistics and corpus-based translation studies.In light of those problems , some possible solutions are proposed , including constructing a super-large-scale English-Chinese Parallel corpus , refining the technology of automatic tagging , developing new software and on-line retrieval platform etc.