Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo khoa học: "Unsupervised Learning of Narrative Schemas and their Participants"

We describe an unsupervised system for learning narrative schemas, coherent sequences or sets of events (arrested(POLICE , SUSPECT), convicted( JUDGE , SUSPECT )) whose arguments are filled with participant semantic roles defined over words (J UDGE = {judge, jury, court}, P OLICE = {police, agent, authorities}). Unlike most previous work in event structure or semantic role learning, our system does not use supervised techniques, hand-built knowledge, or predefined classes of events or roles. Our unsupervised learning algorithm uses coreferring arguments in chains of verbs to learn both rich narrative event structure and argument roles. By jointly addressing both tasks,. | Unsupervised Learning of Narrative Schemas and their Participants Nathanael Chambers and Dan Jurafsky Stanford University Stanford CA 94305 natec jurafsky @stanford.edu Abstract We describe an unsupervised system for learning narrative schemas coherent sequences or sets of events arrested POLICE SUSPECT convicted JUDGE SUSPECT whose arguments are filled with participant semantic roles defined over words Judge judge jury court Police police agent authorities . Unlike most previous work in event structure or semantic role learning our system does not use supervised techniques hand-built knowledge or predefined classes of events or roles. Our unsupervised learning algorithm uses coreferring arguments in chains of verbs to learn both rich narrative event structure and argument roles. By jointly addressing both tasks we improve on previous results in narrative frame learning and induce rich frame-specific semantic roles. 1 Introduction This paper describes a new approach to event semantics that jointly learns event relations and their participants from unlabeled corpora. The early years of natural language processing NLP took a top-down approach to language understanding using representations like scripts Schank and Abelson 1977 structured representations of events their causal relationships and their participants and frames to drive interpretation of syntax and word use. Knowledge structures such as these provided the interpreter rich information about many aspects of meaning. The problem with these rich knowledge structures is that the need for hand construction specificity and domain dependence prevents robust and flexible language understanding. Instead modern work on understanding has focused on shallower representations like semantic roles which express at least one aspect of the semantics of events and have proved amenable to supervised learning from corpora like PropBank Palmer et al. 2005 and Framenet Baker et al. 1998 . Unfortunately creating these supervised