<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1008">
  <Title>Acquiring Inference Rules with TemporalConstraints by Using Japanese Coordinated Sentences and Noun-Verb Co-occurrences</Title>
  <Section position="2" start_page="0" end_page="57" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Our goal is to develop an unsupervised method for acquiring inference rules that describe logical implications between event occurrences. As clues to nd the rules, we chose Japanese coordinated sentences, which typically report two events that occur in a certain temporal order. Of course, not every coordinatedsentence 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 obtaintheruleIfsomeoneenforcesalaw,usuallysome- null 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 fourhuman judges.</Paragraph>
    <Paragraph position="1"> Note that the acquired inference rules pose temporal constraints on occurrences of the events described in the rules. In the enacting-and-enforcing-law example, the constraints were expressed by the phrase at the same time as or beforethe event of. We think suchtemporally constrained rulesshould bebenecial invarioustypesofNLPapplications. Therulesshould allow Q&amp;A systems to guess or restrict the time at which a certain event occurs even if they cannot directly nd the time in given documents. In addition, we foundthat a large part of the acquired rules can be regarded as paraphrases, and many possible applicationsofparaphrases shouldalsobetarget applications. To acquire rules, our method uses a score, which is basically an approximation ofthe probability that particular coordinated sentences will be observed. However, it is weighted by a bias, which embodies our assumption that frequently observed verbs are likely to appear as the consequence of a proper inference rule.</Paragraph>
    <Paragraph position="2"> This is based on our intuition that frequently appearingverbshave a generic meaningandtendto describe a wide range of situations, and that natural language expressions referring to a wide range of situations are more likely to be a consequence of a proper rule than specic expressions describing only a narrowrangeof events. A similar idea relying on word co-occurrence was proposed by Geffet and Dagan (Geffet and Dagan, 2005)but ourmethodis simpler and we expect it to be applicable to a wider range of vocabularies.</Paragraph>
    <Paragraph position="3"> Research on the automatic acquisition of inference rules, paraphrases and entailments has received much attention. Previous attempts have used, for instance, the similarities between case frames (Lin and Pan- null tel, 2001), anchor words (Barzilay and Lee, 2003; Shinyama et al., 2002; Szepektor et al., 2004), and a web-based method(Szepektor et al., 2004;Geffet and Dagan, 2005). There is also a workshop devoted to thistask (Daganetal.,2005). Theobtained accuracies have still been low, however, and we think searching for other clues, such as coordinated sentences and the bias wehave just mentioned, isnecessary. Inaddition, research has also been done on the acquisition of the temporal relations (Fujiki et al., 2003; Chklovski and Pantel, 2004) by using coordinated sentences as we did, but these worksdid not consider the implications between events.</Paragraph>
  </Section>
class="xml-element"></Paper>