Exploratory Study of Word Sense Disambiguation Methods for Verbs in Brazilian Portuguese

Word Sense Disambiguation (WSD) aims at identifying the correct sense of a word in a given context. WSD is an important task for other applications as Machine Translation or Information Retrieval. For English, WSD has been widely studied, obtaining different performances. Analyzing by morphosyntactic class, Verb is the hardest class to be disambiguated. Verbs are an important class and help to the sentence construction. Studies show that the disambiguation of verbs brings improvements into other applications. For Portuguese, there are few studies about WSD and, recently, these have been focused on general purpose. In the present paper, we report an exploratory study of knowledge-based Word Sense Disambiguation methods for verbs in Brazilian Portuguese, using WordNet-Pr (for English) as sense repository; and a comparison with the results obtained for nouns. The results show that, both All-words and Lexical sample evaluation, no methods outperformed the baseline. However, the multi-document scenario helped the WSD task.