<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1132">
  <Title>Probabilistic Models of Verb-Argument Structure</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Recent research into verb-argument structure has has attempted to acquire the syntactic alternation behavior of verbs directly from large corpora. Mc-Carthy (2000), Merlo and Stevenson (2001), and Schulte im Walde (2000) have evaluated their systems' accuracy against human judgments of verb classification, with the comprehensive verb classes of Levin (1993) often serving as a gold standard.</Paragraph>
    <Paragraph position="1"> Another area of research has focused on automatic clustering algorithms for verbs and their arguments with the goal of finding groups of semantically related words (Pereira et al., 1993; Rooth et al., 1999), without focusing specifically on alternation behavior. We aim to bring these strands of research together with a unified probabilistic model of verb argument structure incorporating alternation behavior.</Paragraph>
    <Paragraph position="2"> Unraveling the mapping between syntactic functions such as subject and object and semantic roles such as agent and patient is an important piece of the language understanding problem. Learning the alternation behavior of verbs automatically from unannotated text would significantly reduce the amount of labor needed to create text understanding systems, whether that labor takes the form of writing lexical entries or of annotating semantic information to train statistical systems.</Paragraph>
    <Paragraph position="3"> Our use of generative probabilistic models of argument structure also allows for language modeling applications independent of semantic interpretation.</Paragraph>
    <Paragraph position="4"> Language models based on head-modifier lexical dependencies in syntactic trees have been shown to have lower perplexity than D2-gram language models and to reduce word-error rates for speech recognition (Chelba and Jelinek, 1999; Roark, 2001). Incorporating semantic classes and verb alternation behavior could improve such models' performance.</Paragraph>
    <Paragraph position="5"> Automatically derived word clusters are used in the statistical parsers of Charniak (1997) and Magerman (1995). Incorporating alternation behavior into such models might improve parsing results as well.</Paragraph>
    <Paragraph position="6"> This paper focuses on evaluating probabilistic models of verb-argument structure in terms of how well they model unseen test data, as measured by perplexity. We will examine maximum likelihood bigram and trigram models, clustering models based on those of Rooth et al. (1999), as well as a new probabilistic model designed to capture alternations in verb-argument structure.</Paragraph>
  </Section>
class="xml-element"></Paper>