Acquisition of Computational-Semantic Lexicons from Machine Readable Lexical Resources

Acquisition of Computational-Semantic Lexicons from Machine Readable Lexicai Resources Jason J. S. Chang and J. N. Chen Department of Computer Science National Tsing Hua University Hsinchu 30043, Talwan, ROC Tel: +886 35 731-069 Fax: 723-694 (jschang,dr818314 }@cs.nthu.edu.tw Abstract This paper describes a heuristic algorithm capable of automatically assigning a label to each of the senses in a machine readable dictionary (MRD) for the purpose of acquiring a com- putational-semantic lexicon for treatment of lexical ambiguity. Including these labels in the MRD-based lexical database offers several positive effects. The labels can be used as a coarser sense division so unnecessarily fine sense distinction can be avoided in word sense disambigu- ation (WSD).The algorithm is based primarily on simple word matching between an MRD defi- nition sentence and word lists of an LLOCE topic. We also describe an implementation of the algorithm for labeling definition sentences in Longman Dictionary of Contemporary English (LDOCE). For this purpose the topics and sets of related words in Longman Lexicon of Con- temporary English (LLOCE) are used in this work. Quantitative results for a 12-word test set are reported. Our discussion entails how the availability of these labels provides the means for treating such problems as: acquisition of a lexicon capable of providing broad coverage, sys- tematic word sense shifts, lexical underspecification, and acquisition of zero-derivatives. 1. Introduction Treatment of lexical ambiguity such as WSD has been found useful in many NLP applications, includ- ing information retrieval (McRoy 1992; Krovetz and Croft 1992) and machine translation (Brown et al. 1991; Dagan et al. 1991; Dagan and Itai 1994). Recently, various approaches (Dolan 1994; Luk 1995; Yarowsky 1992; Dagan et al. 1991 ;Dagan and Itai 1994) to word sense division have been used in WSD research. Directly using dictionary senses as the sense division has several advantages. First, sense distinc- tion according to a dictionary is readily available from MRDs such as the LDOCE (Longman 1992). Sec- ond, indicative words and concepts for each sense are directly available in numbered definitions and examples. Lesk (1986) demonstated that dictionary entries can be used to generate signatures of senses for WSD. However, using MRD as the knowledge source for sense division and disambiguation encounters certain problems. Dolan (1994) observed that sense division in MRD is frequently too free for the purpose of WSD. A WSD system based on dictionary senses faces an unnecessary and difficult "forced-choices." Most researchers resorted to human intervention to identify and group closely related senses. This paper describes a heuristic algorithm capable of automatically assigning a label to each of the senses in a machine readable dictionary (MRD) for the purpose of acquiring a computational-semantic lex- icon for treatment of lexical ambiguity. Including these labels in the MRD-based lexical database offers several positive effects. The labels can be used as a coarser sense division so unnecessarily fine sense dis- tinction can be avoided in word sense disambiguation (WSD). The algorithm is based primarily on simple word matching between an MRD definition sentence and word lists …

Content truncated to 500 words