Extracting Terminologically Relevant Collocations in the Translation of Chinese Monograph

R. Dale et al. (Eds.): IJCNLP 2005, LNAI 3651, pp. 1017 – 1028, 2005. © Springer-Verlag Berlin Heidelberg 2005 Extracting Terminologically Relevant Collocations in the Translation of Chinese Monograph* Byeong-Kwu Kang, Bao-Bao Chang, Yi-Rong Chen, and Shi-Wen Yu The Institute of Computational Linguistics, Peking University, Beijing, 100871，China {kbg43, chbb, chenyr, yusw}@pku.edu.cn Abstract. This paper suggests a methodology which is aimed to extract the terminologically relevant collocations for translation purposes. Our basic idea is to use a hybrid method which combines the statistical method and linguistic rules. The extraction system used in our work operated at three steps: (1) Tokenization and POS tagging of the corpus; (2) Extraction of multi-word units using statistical measure; (3) Linguistic filtering to make use of syntactic patterns and stop-word list. As a result, hybrid method using linguistic filters proved to be a suitable method for selecting terminological collocations, it has considerably improved the precision of the extraction which is much higher than that of purely statistical method. In our test, hybrid method combining “Log-likelihood ratio” and “linguistic rules” had the best performance in the extraction. We believe that terminological collocations and phrases extracted in this way, could be used effectively either to supplement existing terminological collections or to be used in addition to traditional reference works. 1 Introduction Communication between different individuals and nations is not always easy, especially when more than one language is involved. This kind of communication can include translation problems, which can be solved by the translators who bridge the gap between two different languages. Through the past decade, China and Korea have been undergoing large economic, cultural exchange, which invariably affects all aspects of communication, particularly translation. New international contacts, foreign investments as well as cross-cultural communication have caused an enormous increase in the volume of translations produced and required. But by now, most of all this translation work has been conducted by translators alone, which bears the burden of an enormous translation task to them. In order to accomplish these tasks with maximum efficiency and quality, a new translation method supported by computer technology has been suggested. MAHT, also known as computer-assisted translation involves some interaction between translator and the computer. It seems to be more suited for the needs of many * This work has been supported by The National Basic Research Program of China(973 program, No. 2004CB318102) and the 863 program (No. 2001AA114210, 2002AA117010). 1018 B.-K. Kang et al. organizations which have to handle the translation of the documents. Computer- assisted translation systems are based on “translation memory” and “terminology databases”. With translation memory tools, translators have immediate access to previous translations of the text, which they can then accept or modify. Terminology management systems also can prove very useful in supporting translator’s work [2, 11]. Most translators use some sort of glossary or terminology database, especially in the translation of the technical documents or academic monograph. Many translation bureaux have the collection of the terminology data bases. But time pressure and costs make it difficult to …

Content truncated to 500 words