tailieunhanh - Báo cáo khoa học: "Learning Syntactic Verb Frames Using Graphical Models"

We present a novel approach for building verb subcategorization lexicons using a simple graphical model. In contrast to previous methods, we show how the model can be trained without parsed input or a predefined subcategorization frame inventory. Our method outperforms the state-of-the-art on a verb clustering task, and is easily trained on arbitrary domains. | Learning Syntactic Verb Frames Using Graphical Models Thomas Lippincott University of Cambridge Computer Laboratory United Kingdom tl318@ Diarmuid O Seaghdha University of Cambridge Computer Laboratory United Kingdom do242@ Anna Korhonen University of Cambridge Computer Laboratory United Kingdom alk23@ Abstract We present a novel approach for building verb subcategorization lexicons using a simple graphical model. In contrast to previous methods we show how the model can be trained without parsed input or a predefined subcategorization frame inventory. Our method outperforms the state-of-the-art on a verb clustering task and is easily trained on arbitrary domains. This quantitative evaluation is complemented by a qualitative discussion of verbs and their frames. We discuss the advantages of graphical models for this task in particular the ease of integrating semantic information about verbs and arguments in a principled fashion. We conclude with future work to augment the approach. 1 Introduction Subcategorization frames SCFs give a compact description of a verb s syntactic preferences. These two sentences have the same sequence of lexical syntactic categories VP-NP-SCOMP but the first is a simple transitive X understood Y while the second is a ditransitive with a sentential complement X persuaded Y that Z 1. Kim VP understood NP the evidence SCOMP that Sandy was present 2. Kim VP persuaded NP the judge SCOMP that Sandy was present An SCF lexicon would indicate that persuade is likely to take a direct object and sentential complement NP-SCOMP while understand is more likely to take just a direct object NP . A comprehensive lexicon would also include semantic information about selectional preferences or restrictions on argument heads of verbs diathesis alternations . semantically-motivated alternations between pairs of SCFs and a mapping from surface frames to the underlying predicate-argument structure. Information about verb .