Semi-Automatic Identification of Bilingual Synonymous Technical Terms from Phrase Tables and Parallel Patent Sentences

Semi-Automatic Identification of Bilingual Synonymous Technical Terms from Phrase Tables and Parallel Patent Sentences Bing Liang a, Takehito Utsuro b, and Mikio Yamamoto b aGraduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, 305-8573, JAPAN bFaculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, 305-8573, JAPAN Abstract. In the research field of machine translation of patent documents, the issue of ac- quiring technical term translation equivalent pairs automatically from parallel patent docu- ments is one of those most important. We take an approach of utilizing the phrase table of a state-of-the-art phrase-based statistical machine translation model. In this task, we con- sider situations where a technical term is observed in many parallel patent sentences and is translated into many translation equivalents. We apply SVM to the task of identifying synonymous translation equivalent pairs and achieve almost 98% precision and over 40% F- measure. Then, in order to improve recall, we introduce a semi-automatic framework, where we employ the strategy of selecting more than one seeds for each set of candidates bilingual synonymous term pairs. By manually judging whether each pair of two seeds is synonymous or not, we achieve over 95% precision and 50% recall. Keywords: Bilingual Lexicon Acquisition, Synonyms, Phrase Tables 1 Introduction For both high quality machine and human translation, a large scale and high quality bilingual lex- icon is the most important key resource. Since manual compilation of bilingual lexicon requires plenty of time and huge manual labor, in the research area of knowledge acquisition from natural language text, automatic bilingual lexicon compilation have been studied. Techniques invented so far include translation term pair acquisition based on statistical co-occurrence measure from par- allel sentences (Matsumoto and Utsuro, 2000), translation term pair acquisition from comparable corpora (Fung and Yee, 1998), compositional translation generation based on an existing bilingual lexicon for human use (Tonoike et al., 2006), and translation term pair acquisition by collecting partially bilingual texts through the search engine (Huang et al., 2005). Among those efforts of acquiring bilingual lexicon from text, Morishita et al. (2008) studied to acquire technical term translation lexicon from phrase tables, which are trained by a phrase- based statistical machine translation model with parallel sentences automatically extracted from parallel patent documents. Recently, we further studied to require the acquired technical term translation equivalents to be consistent with word alignment in parallel sentences and achieved 91.9% precision with almost 70% recall. This technique has been actually adopted by a Japanese organization which is responsible for translating Japanese patent applications published by the Japanese Patent Office (JPO) into English, where it has been utilized in the process of semi- automatically compiling bilingual technical term lexicon from parallel patent sentences. In this process, persons who are working on compiling bilingual technical term lexicon judge whether to accept or not candidates of bilingual technical term pairs presented by the system. Copyright 2011 by Bing Liang, Takehito Utsuro, and Mikio Yamamoto 25th Pacific Asia Conference on Language, Information and Computation, pages 196–205 196 Based …

Content truncated to 500 words