Acquiring Inference Rules with Temporal Constraints by Using Japanese Coordinated Sentences and Noun-Verb Co-occurrences

Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL, pages 57–64, New York, June 2006. c⃝2006 Association for Computational Linguistics Acquiring Inference Rules with Temporal Constraints by Using Japanese Coordinated Sentences and Noun-Verb Co-occurrences Kentaro Torisawa Japan Advanced Institute of Science and Technology 1-1 Asahidai, Nomi-shi, Ishikawa-ken, 923-1211 JAPAN torisawa@jaist.ac.jp Abstract This paper shows that inference rules with temporal constraints can be acquired by us- ing verb-verb co-occurrences in Japanese coordinated sentences and verb-noun co- occurrences. For example, our unsuper- vised acquisition method could obtain the inference rule “If someone enforces a law, usually someone enacts the law at the same time as or before the enforcing of the law” since the verbs “enact” and “enforce” frequently co-occurred in coordinated sen- tences and the verbs also frequently co- occurred with the noun “law”. We also show that the accuracy of the acquisition is improved by using the occurrence fre- quency of a single verb, which we assume indicates how generic the meaning of the verb is. 1 Introduction Our goal is to develop an unsupervised method for acquiring inference rules that describe logical impli- cations between event occurrences. As clues to Þnd the rules, we chose Japanese coordinated sentences, which typically report two events that occur in a cer- tain temporal order. Of course, not every coordi- nated sentence necessarily expresses implications. We found, though, that reliable rules can be acquired by looking at co-occurrence frequencies between verbs in coordinated sentences and co-occurrences between verbs and nouns. For example, our method could ob- tain the rule “If someone enforces a law, usually some- one enacts the law at the same time as or before the enforcing of the law”. In our experiments, when our method produced 400 rules for 1,000 given nouns, 70% of the rules were considered proper by at least three of four human judges. Note that the acquired inference rules pose tempo- ral constraints on occurrences of the events described in the rules. In the “enacting-and-enforcing-law” ex- ample, the constraints were expressed by the phrase “at the same time as or before the event of”. We think such temporally constrained rules should be beneÞcial in various types of NLP applications. The rules should allow Q&A systems to guess or restrict the time at which a certain event occurs even if they cannot di- rectly Þnd the time in given documents. In addition, we found that a large part of the acquired rules can be regarded as paraphrases, and many possible applica- tions of paraphrases should also be target applications. To acquire rules, our method uses a score, which is basically an approximation of the probability that par- ticular coordinated sentences will be observed. How- ever, it is weighted by a bias, which embodies our as- sumption that frequently observed verbs are likely to appear as the consequence of a proper inference rule. This is based on our intuition that frequently appear- ing verbs have a generic meaning and tend to describe …

Content truncated to 500 words