[工程科技]Automatic Verb Classication Based on Statistical Distributions of Argument Structure.pdfVIP

Automatic Verb Classication Based on Statistical Distributions of Argument Structure Paola Merlo¤ Suzanne Stevensony University of Geneva University of Toronto Automatic acquisition of lexical knowledge is critical to a wide range of natural language pro- cessing tasks. Especially important is knowledge about verbs, which are the primary source of relational information in a sentence—the predicate-argumen t structure that relates an action or state to its participants (i.e., who did what to whom). In this work, we report on super- vised learning experiments to automatically classify three major types of English verbs, based on their argument structure—speci cally, the thematic roles they assign to participants . We use linguistically-motivated statistical indicators extractedfro m large annotated corpora to train the classi er, achieving 69.8% accuracy fo r a task whose baseline is 34%, and whose expert-based upper bound we calculate at 86.5%. A detailed analysis of the performance of the algorithm and of its errors con rms that the proposedfeature s capture properties related to the argument struc- ture of the verbs. Our results validate our hypotheses that knowledge about thematic relations is crucial fo r verb classi cation, and that it can be gleaned fro m a corpus by automatic means. We thus demonstrate an effective combination of deeper linguistic knowledge with the robustness and scalability of statistical techniques. 1. Introduction Automatic acquisition of lexical knowledge is critical to a wide range of natural lan- guage processing (NLP) tasks (Boguraev and Pustejovsky 1996). Especially important is knowledge about verbs, which are the primary source of relational information in a sentence—the predicate-argumen t structure that relates an action or state to its par- ticipants (i.e., who did what to whom). In fa