Automatic Acquisition of Script Knowledge from a Text Collection

Automatic Acquisition of Script Knowledge from a Text Collection Toshiaki Fujiki� Hidetsugu Nanba Interdisciplinary Graduate School of Graduate School of Science and Engineering� Information Sciences Tokyo Institute of Technology 4259 Nagatsuta-cho, Midori-ku, Yokohama, JAPAN Hiroshima City University 3-4-1 Otsukahigashi, Asaminami-ku, Hiroshima, Manabu Okumura Precision and Intelligence Laboratory Tokyo Institute of Technology 4259 Nagatsuta-cho, Midori-ku, fujiki@lr.pi.titech.ac.jp�Yokohama, JAPAN JAPAN� oku@pi.titech.ac.jp nanba@its.hiroshima-cu.ac.jp Abstract In this paper, we describe a method for automatic acquisition of script knowl- edge from a Japanese text collection. Script knowledge represents a typical sequence of actions that occur in a particular situation. We extracted se- quences (pairs) of actions occurring in time order from a Japanese text collec- tion and then chose those that were typi- cal of certain situations by ranking these sequences (pairs) in terms of the fre- quency 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 in time order. We also describe a preliminary exper- iment 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 par- ticular 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 lan- guage processing, especially for word sense dis- ambiguation, text generation, and automatic text summarization(Dejong, 1982). However, most studies have used only small portions of script knowledge manually generated by the authors. We need a large-scale knowledge database; however, manually producing such a database would cost too much. In this paper, we propose a method for au- tomatic acquisition of script knowledge from a Japanese text collection. Because script knowl- edge represents a typical sequence of actions formed in a particular situation, we extracted se- quences (pairs) of actions that occur in time order. We then chose among these actions the ones that are typical by ranking them in terms of the fre- quency of their occurrence. To extract sequences of actions that occur in time order, we constructed a text collection in which texts describing facts re- lating to a similar situation were clustered together and arranged in time order. In Section 2, we describe our proposed method and show how we constructed the text collection. In Section 3, we describe a preliminary experi- ment with our acquisition system and discuss the results. 2 Proposed Method Our method consists of the following three steps: 1. Constructing a text collection. 91 2. Extracting sequences (pairs) of actions from the text collection. 3. Selecting typical sequences. We …

Content truncated to 500 words