Acquiring Event Relation Knowledge by Learning Cooccurrence Patterns and Fertilizing Cooccurrence Samples with Verbal Nouns

Acquiring Event Relation Knowledge by Learning Cooccurrence Patterns and Fertilizing Cooccurrence Samples with Verbal Nouns 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 Aiming at acquiring semantic relations be- tween events from a large corpus, this paper proposes several extensions to a state-of-the- art method originally designed for entity re- lation extraction, reporting on the present re- sults of our experiments on a Japanese Web corpus. The results show that (a) there are indeed specific cooccurrence patterns use- ful for event relation acquisition, (b) the use of cooccurrence samples involving ver- bal nouns has positive impacts on both re- call and precision, and (c) over five thou- sand relation instances are acquired from a 500M-sentence Web corpus with a precision of about 66% for action-effect relations. 1 Introduction The growing interest in practical NLP applications such as question answering, information extraction and multi-document summarization places increas- ing demands on the processing of relations between textual fragments such as entailment and causal rela- tions. Such applications often need to rely on a large amount of lexical semantic knowledge. For exam- ple, a causal (and entailment) relation holds between the verb phrases wash something and something is clean, which reflects the commonsense notion that if someone has washed something, this object is clean as a result of the washing event. A crucial issue is how to obtain and maintain a potentially huge col- lection of such event relations instances. Motivated by this background, several research groups have reported their experiments on automatic acquisition of causal, temporal and entailment re- lations between event mentions (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, etc.). The com- mon idea behind them is to use a small number of manually selected generic lexico-syntactic cooccur- rence patterns (LSPs or simply patterns). to Verb-X and then Verb-Y, for example, is used to obtain tem- poral relations such as marry and divorce (Chklovski and Pantel, 2005). The use of such generic patterns, however, tends to be high recall but low precision, which requires an additional component for pruning extracted relations. This issue has been addressed in basically two approaches, either by devising heuris- tic statistical scores (Chklovski and Pantel, 2005; Torisawa, 2006; Zanzotto et al., 2006) or training classifiers for disambiguation with heavy supervi- sion (Inui et al., 2003). This paper explores a third way for enhancing present LSP-based methods for event relation acqui- sition. The basic idea is inspired by the following recent findings in relation extraction (Ravichandran and Hovy, 2002; Pantel and Pennacchiotti, 2006, etc.), which aims at extracting semantic relations be- tween entities (as opposed to events) from texts. (a) The use of generic patterns tends to be high recall but low precision, which requires an additional com- ponent for pruning. (b) On the other hand, there are specific patterns that are highly reliable but they are much …

Content truncated to 500 words