Second language information transfer in automatic verb classification: A preliminary investigation

Lexical semantic classes incorporate both syntactic and semantic information about verbs. Lexical semantic classification of verbs provide a great deal of useful information about the possible usage of each verb. In our work, we explore the use of multilingual corpora in the automatic learning of verb classification. We extend the work of Merlo and Stevenson (2001a), in which statistics on simple syntactic features extracted from textual corpora were used to train an automatic classifier for three lexical semantic classes of English verbs. We hypothesize that some lexical semantic features which are difficult to detect superficially in English may manifest themselves syntactically in another language. In our two-way classification task, features from multiple languages achieve an accuracy as high as 81%, making a small bitext a useful alternative to using a large monolingual corpus for verb classification. In this thesis, experimental results are presented and future extensions are discussed.