Two-Phased Event Relation Acquisition: Coupling the Relation-Oriented and Argument-Oriented Approaches

Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 1–8 Manchester, August 2008 Two-Phased Event Relation Acquisition: Coupling the Relation-Oriented and Argument-Oriented Approaches Shuya Abe Kentaro Inui Yuji Matsumoto Graduate School of Information Science, Nara Institute of Science and Technology {shuya-a,inui,matsu}@is.naist.jp Abstract Addressing the task of acquiring semantic relations between events from a large cor- pus, we first argue the complementarity be- tween the pattern-based relation-oriented approach and the anchor-based argument- oriented approach. We then propose a two- phased approach, which first uses lexico- syntactic patterns to acquire predicate pairs and then uses two types of anchors to iden- tify shared arguments. The present results of our empirical evaluation on a large-scale Japanese Web corpus have shown that (a) the anchor-based filtering extensively im- proves the accuracy of predicate pair ac- quisition, (b) the two types of anchors are almost equally contributive and combining them improves recall without losing accu- racy, and (c) the anchor-based method also achieves high accuracy in shared argument identification. 1 Introduction The growing interest in practical NLP applications such as question answering, information extrac- tion and multi-document summarization places in- creasing demands on the processing of relations between textual fragments such as entailment and causal relations. Such applications often need to rely on a large amount of lexical semantic knowl- edge. For example, a causal (and entailment) rela- tion holds between the verb phrases wash some- thing and something is clean, which reflects the commonsense notion that if someone has washed c⃝ 2008. Licensed under the Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported li- cense (http://creativecommons.org/licenses/by-nc-sa/3.0/). Some rights reserved. something, this object is clean as a result of the washing event. A crucial issue is how to ob- tain and maintain a potentially huge collection of such event relation instances. This paper addresses the issue of how to automatically acquire such in- stances of relations between events (henceforth, event relation instances) from a large-scale text collection. Motivated by this issue, several research groups have reported their experiments on automatic ac- quisition of causal, temporal and entailment rela- tions between event expressions (typically verbs or verb phrases) (Lin and Pantel, 2001; Inui et al., 2003; Chklovski and Pantel, 2005; Torisawa, 2006; Pekar, 2006; Zanzotto et al., 2006; Abe et al., 2008, etc.). As we explain below, however, none of these studies fully achieves the goal we pursue in this paper. An important aspect to consider in event relation acquisition is that each event has arguments. For example, the causal relation between wash some- thing and something is clean can be represented naturally as: (1) wash(obj:X) →cause is clean(subj:X), where X is a logical variable denoting that the filler of the object slot of the wash event should be shared (i.e. identical) with the filler of the subject slot of the is clean event. To be more general, an instance of a given rela- tion R can be represented as: (2) pred1(arg1:X) →R pred2(arg2:X), where predi is a natural language predicate, typ- ically a verb …

Content truncated to 500 words