[工程科技]Automaticverbclassificationbasedonstatisticaldistributionsofargumentstructure.pdfVIP

Automatic Verb Classification Based on Statistical Distributions of Argument Structure Paola Merlo* S u z a n n e S t e v e n s o n t 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-argument 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--specifically, the thematic roles they assign toparticipants. We use linguistically-motivated statistical indicators extractedfrom large annotated corpora to train the classifier, achieving 69.8% accuracyfor 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 theproposedfeatures captureproperties related to the argument struc- ture of the verbs. Our results validate our hypotheses that knowledge about thematic relations is crucialfor verb classification, and that it can be gleanedfrom 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 impo