tailieunhanh - Báo cáo khoa học: "Verb Classification using Distributional Similarity in Syntactic and Semantic Structures"

In this paper, we propose innovative representations for automatic classification of verbs according to mainstream linguistic theories, namely VerbNet and FrameNet. First, syntactic and semantic structures capturing essential lexical and syntactic properties of verbs are defined. Then, we design advanced similarity functions between such structures, ., semantic tree kernel functions, for exploiting distributional and grammatical information in Support Vector Machines. | Verb Classification using Distributional Similarity in Syntactic and Semantic Structures Danilo Croce University of Tor Vergata 00133 Roma Italy croce@ Roberto Basili University of Tor Vergata 00133 Roma Italy basili@ Alessandro Moschitti University of Trento 38123 Povo TN Italy moschitti@ Martha Palmer University of Colorado at Boulder Boulder CO 80302 USA mpalmer@ Abstract In this paper we propose innovative representations for automatic classification of verbs according to mainstream linguistic theories namely VerbNet and FrameNet. First syntactic and semantic structures capturing essential lexical and syntactic properties of verbs are defined. Then we design advanced similarity functions between such structures . semantic tree kernel functions for exploiting distributional and grammatical information in Support Vector Machines. The extensive empirical analysis on VerbNet class and frame detection shows that our models capture meaningful syntactic semantic structures which allows for improving the state-of-the-art. 1 Introduction Verb classification is a fundamental topic of computational linguistics research given its importance for understanding the role of verbs in conveying semantics of natural language NL . Additionally generalization based on verb classification is central to many NL applications ranging from shallow semantic parsing to semantic search or information extraction. Currently a lot of interest has been paid to two verb categorization schemes VerbNet Schuler 2005 and FrameNet Baker et al. 1998 which has also fostered production of many automatic approaches to predicate argument extraction. Such work has shown that syntax is necessary for helping to predict the roles of verb arguments and consequently their verb sense Gildea and Juras-fky 2002 Pradhan et al. 2005 Gildea and Palmer 2002 . However the definition of models for optimally combining lexical and syntactic constraints is 263 .