<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2104">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Comparison of Alternative Parse Tre Paths for Labeling Semantic Roles</Title>
  <Section position="3" start_page="0" end_page="811" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A persistent goal of natural language processing research has been the automated transformation of natural language texts into representations that unambiguously encode their propositional content in formal notation. Increasingly, first-order predicate calculus representations of textual meaning have been used in natural lanugage processing applications that involve automated inference. For example, Moldovan et al. (203) demonstrate how predicate-argument formulations of questions and candidate answer sentences are unified using logical inference in a top-performing question-answering application.</Paragraph>
    <Paragraph position="1"> The importance of robust techniques for predicate-argument transformation has motivated the development of large-scale text corpora with predicate-argument annotations such as PropBank (Palmer et al., 205) and FrameNet (Baker et al., 198). These corpora typically take a pragmatic approach to the predicate-argument representations of sentences, where predicates correspond to single word trigers in the surface form of the sentence (typically verb lemmas), and arguments can be identified as substrings of the sentence.</Paragraph>
    <Paragraph position="2"> Along with the development of annotated corpora, researchers have developed new techniques for automatically identifying the arguments of predications by labeling text segments in sentences with semantic roles. Both Gildea &amp; Jurafsky (202) and Palmer et al.</Paragraph>
    <Paragraph position="3"> (205) describe statistical labeling algorithms that achieve high accuracy in assigning semantic role labels to appropropriate constituents in a parse tree of a sentence. Each of these efforts employed the use of parse tree paths as predictive features, encoding the series of up and down transitions through a parse tree to move from the node of the verb (predicate) to the governing node of the constituent (argument).</Paragraph>
    <Paragraph position="4"> Palmer et al. (205) demonstrate that utilizing the gold-standard parse trees of the Penn tree-bank (Marcus et al., 193) to encode parse tree paths yields significantly better labeling accuracy than when using an automatic syntactical parser, namely that of Colins (199).</Paragraph>
    <Paragraph position="5">  Parse tree paths (between verbs and arguments that fil semantic roles) are particularly interesting because they symbolically encode the relationship between the syntactic and semantic aspects of verbs, and are potentially generalized acros other verbs within the same class (Levin, 193). However, the encoding of individual parse tree paths for predicates is wholy dependent on the characteristics of the parse tree of a sentence, for which competing approaches could be taken.</Paragraph>
    <Paragraph position="6"> The research effort described in this paper further explores the role of parse tree paths in identifying the argument structure of verb-based predications. We are particularly interested in exploring alternatives to the constituency parses that were used in previous research, including parsing approaches that employ dependency grammars. Specifically, our aim is to answer four important questions: 1. How can parse tree paths be encoded when employing different automated constituency parsers, i.e. Charniak (200), Klein &amp; Maning (203), or a dependency parser (Lin, 198)? 2. Given that each of these alternatives creates a different formulation of the parse tree of a sentence, which of them encodes branches that are easiest to align with substrings that have been annotated with semantic role information? 3. What is the relative precision and recall performance of parse tree paths formulated using these alternative automated parsing techniques, and do the results vary depending on argument type? 4. How many examples of parse tree paths are necessary to provide as training examples in order to achieve high labeling accuracy when employing each of these parsing alternatives? Each of these four questions is addressed in the four subsequent sections of this paper, followed by a discusion of the implications of our findings and directions for future work.</Paragraph>
  </Section>
class="xml-element"></Paper>