<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1006">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Kernel-Based Pronoun Resolution with Structured Syntactic Knowledge</Title>
  <Section position="3" start_page="0" end_page="41" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Pronoun resolution is the task of finding the correct antecedent for a given pronominal anaphor in a document. Prior studies have suggested that syntactic knowledge plays an important role in pronoun resolution. For a practical pronoun resolution system, the syntactic knowledge usually comes from the parse trees of the text. The issue that arises is how to effectively incorporate the syntactic information embedded in the parse trees to help resolution. One common solution seen in previous work is to define a set of features that represent particular syntactic knowledge, such as the grammatical role of the antecedent candidates, the governing relations between the candidate and the pronoun, and so on. These features are calculated by mining the parse trees, and then could be used for resolution by using manually designed rules (Lappin and Leass, 1994; Kennedy and Boguraev, 1996; Mitkov, 1998), or using machine-learning methods (Aone and Bennett, 1995; Yang et al., 2004; Luo and Zitouni, 2005).</Paragraph>
    <Paragraph position="1"> However, such a solution has its limitation. The syntactic features have to be selected and defined manually, usually by linguistic intuition. Unfortunately, what kinds of syntactic information are effective for pronoun resolution still remains an open question in this research community. The heuristically selected feature set may be insufficient to represent all the information necessary for pronoun resolution contained in the parse trees.</Paragraph>
    <Paragraph position="2"> In this paper we will explore how to utilize the syntactic parse trees to help learning-based pronoun resolution. Specifically, we directly utilize the parse trees as a structured feature, and then use a kernel-based method to automatically mine the knowledge embedded in the parse trees. The structured syntactic feature, together with other normal features, is incorporated in a trainable model based on Support Vector Machine (SVM) (Vapnik, 1995) to learn the decision classifier for resolution.</Paragraph>
    <Paragraph position="3"> Indeed, using kernel methods to mine structural knowledge has shown success in some NLP applications like parsing (Collins and Duffy, 2002; Moschitti, 2004) and relation extraction (Zelenko et al., 2003; Zhao and Grishman, 2005). However, to our knowledge, the application of such a technique to the pronoun resolution task still remains unexplored.</Paragraph>
    <Paragraph position="4"> Compared with previous work, our approach has several advantages: (1) The approach utilizes the parse trees as a structured feature, which avoids the efforts of decoding the parse trees into a set of syntactic features in a heuristic manner.</Paragraph>
    <Paragraph position="5"> (2) The approach is able to put together the structured feature and the normal flat features in a trainable model, which allows different types of  information to be considered in combination for both learning and resolution. (3) The approach is applicable for practical pronoun resolution as the syntactic information can be automatically obtained from machine-generated parse trees. And our study shows that the approach works well under the commonly available parsers.</Paragraph>
    <Paragraph position="6"> We evaluate our approach on the ACE data set.</Paragraph>
    <Paragraph position="7"> The experimental results over the different domains indicate that the structured syntactic feature incorporated with kernels can significantly improve the resolution performance (by 5%[?]8% in the success rates), and is reliably effective for the pronoun resolution task.</Paragraph>
    <Paragraph position="8"> The remainder of the paper is organized as follows. Section 2 gives some related work that utilizes the structured syntactic knowledge to do pronoun resolution. Section 3 introduces the framework for the pronoun resolution, as well as the baseline feature space and the SVM classifier.</Paragraph>
    <Paragraph position="9"> Section 4 presents in detail the structured feature and the kernel functions to incorporate such a feature in the resolution. Section 5 shows the experimental results and has some discussion. Finally, Section 6 concludes the paper.</Paragraph>
  </Section>
class="xml-element"></Paper>