Lexicon-to-Ontology Concept Association Using a Bilingual Dictionary

LEXICON-TO-ONTOLOGY CONCEPT ASSOCIATION USING A BILINGUAL DICTIONARY Akitoshi Okumura1 Eduard Hovy Information Technology Research. Labs. Information Sciences Institute NEC Corp. University of Southern California 4-1-1 Miyazaki, Miyamae-ku 4676 Admiralty Way Kawasaki, Japan 216 Marina del Rey, CA 90292-6695 email: okumura@hum.cl.nec.co.jp email: hovy@isi.edu Abstract This paper describes a semi-automatic method for associating a Japanese lexicon with a se- mantic concept taxonomy called an ontology, using a Japanese-English bilingual dictionary as a "bridge". The ontology supports semantic processing in a knowledge-based machine translation system by providing a set of language-neutral symbols with semantic information. To put the ontology to use, lexical items of each language of interest must be linked to appropriate ontology items. The association of ontology items with lexical items of various languages is a process fraught with difficulty: since much of this work depends on the subjective decisions of human workers, large MT dictionaries tend to be subject to some dispersion and inconsistency. The problem we focus on here is how to associate concepts in the ontology with Japanese lexical entities by automatic methods, since it is too difficult to define adequately many concepts man- ually. We have designed three algorithms to associate a Japanese lexicon with the concepts of the ontology: the equivalent-word match, the argument match, and the example match. 1 Introduction This paper describes a semi-automatic method for associating a Japanese lexicon with a semantic concept taxonomy using a Japanese-English bilingual dictionary as a "bridge", in order to support semantic processing in a knowledge-based machine translation (MT) system. Many language processing systems include networks of concepts called ontologies or semantic taxonomies [Bateman 90, Carlson & Nirenburg 90, Hovy & Knight 93, Klavans et al. 90, Knight 93]. These ontologies house the representation symbols used by the analyzer and generator. To put the ontologies to practical use, lexical items of each language of interest must be linked to appro- priate ontology items. To support extensibility to new languages, the MT ontology should be language-neutral, if not language-independent [Hovy & Nirenburg 92]. However, the construction of language-neutral ontologies, and the association of ontology items with lexical items of various languages, is difficult. Since much of this work depends on the subjective decisions of more than one human workers, large MT dictionaries tend to be subject to some dispersion and inconsistency. l This work was done during a visit by the first author to the USC Information Sciences Institute. 177 Many translation errors are due to these dictionary problems. If possible, the dictionary qual- ity should be controlled by automatic algorithms during the process of development to suppress dispersions and inconsistencies, even if the final check is entrusted to humans. Another motivation for automated dictionary/ontology alignment algorithms is the increased availability of online lexical and semantic resources, such as lexicons, taxonomies, dictionaries and thesauri [Matsumoto et al. 93b, Miller 90, Lenat & Guha 90, Carlson & Nirenburg 90, Collins 71, IPAL 87]. Starting with such resources leads to higher quality translation with lower development cost [Hovy & Knight 93, …

Content truncated to 500 words