A Method of Adding New Entries to a Valency Dictionary by Exploiting Existing Lexical Resources

Information on subcategorization and selectional restrictions in a valency dictionary is very important for natural language processing in tasks such as monolingual parsing, accurate rule-based machine translation and automatic summarization. However, adding this detailed information is both time consuming and costly. In this paper we present a method of assigning valency information and selectional restrictions to entries in a bilingual dictionary, based on information in an existing valency dictionary. The method is based on two basic assumptions: words with similar meaning have similar subcategorization frames and selectional restrictions; and words with the same translations have similar meanings. Based on these assumptions, new valency entries are constructed for words in a plain bilingual dictionary, using entries with similar Japanese meaning and the same English translations. The measurement of similarity in Japanese is done using paraphrased examples, so that non-expert native speakers can carry out the task. An initial evaluation of 171 new patterns showed that adding them to a Japaneseto-English machine translation system improved the translation for 31% of sentences using these verbs, and degraded it for 8%, a clear improvement in quality.