Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
In this paper, we describe a method for automatic acquisition of script knowledge from a Japanese text collection. Script knowledge represents a typical sequence of actions that occur in a particular situation. We extracted sequences (pairs) of actions occurring in time order from a Japanese text collection and then chose those that were typical of certain situations by ranking these sequences (pairs) in terms of the frequency of their occurrence. To extract sequences of actions occurring in time order, we constructed a text collection in which texts describing facts relating to a similar situation were clustered together and arranged. | Automatic Acquisition of Script Knowledge from a Text Collection Toshiaki Fujiki Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology 4259 Nagatsuta-cho Midori-ku Yokohama JAPAN fujiki@lr.pi.titech.ac.jp nanba@its.Hiroshima-cu.ac.jp Hidetsugu Nanba Graduate School of Information Sciences Hiroshima City University 3-4-1 Otsukahigashi Asaminami-ku Hiroshima JAPAN Manabu Okumura Precision and Intelligence Laboratory Tokyo Institute of Technology 4259 Nagatsuta-cho Midori-ku Yokohama JAPAN oku@pi.titech.ac.jp Abstract In this paper we describe a method for automatic acquisition of script knowledge from a Japanese text collection. Script knowledge represents a typical sequence of actions that occur in a particular situation. We extracted sequences pairs of actions occurring in time order from a Japanese text collection and then chose those that were typical of certain situations by ranking these sequences pairs in terms of the frequency of their occurrence. To extract sequences of actions occurring in time order we constructed a text collection in which texts describing facts relating to a similar situation were clustered together and aưanged in time order. We also describe a preliminary experiment with our acquisition system and discuss the results. 1 Introduction Script is a term proposed by Schank and it refers to a form of knowledge representation. Script knowledge is a body of knowledge that describes a typical sequence of actions people do in a particular situation Schank and Abelson 1977 . For example when we go to a restaurant we usually enter the restaurant wait sit down get the menu and decide what to eat order the dish wait until the dish has come and so on. This sequence can be said to be script knowledge in the situation of eating at a restaurant . Script knowledge has been used in natural language processing especially for word sense disambiguation text generation and automatic text summarization Dejong 1982 . However
