<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1018">
  <Title>A Mention-Synchronous Coreference Resolution Algorithm Based on the Bell Tree Xiaoqiang Luo and Abe Ittycheriah</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper, we will adopt the terminologies used in the Automatic Content Extraction (ACE) task (NIST, 2003). Coreference resolution in this context is defined as partitioning mentions into entities. A mention is an instance of reference to an object, and the collection of mentions referring to the same object in a document form an entity. For example, in the following sentence, mentions are underlined: &amp;quot;The American Medical Association voted yesterday to install the heir apparent as its president-elect, rejecting a strong, upstart challenge by a District doctor who argued that the nation's largest physicians' group needs stronger ethics and new leadership.&amp;quot; &amp;quot;American Medical Association&amp;quot;, &amp;quot;its&amp;quot; and &amp;quot;group&amp;quot; belong to the same entity as they refer to the same object. null Early work of anaphora resolution focuses on finding antecedents of pronouns (Hobbs, 1976; Ge et al., 1998; Mitkov, 1998), while recent advances (Soon et al., 2001; Yang et al., 2003; Ng and Cardie, 2002; Ittycheriah et al., 2003) employ statistical machine learning methods and try to resolve reference among all kinds of noun phrases (NP), be it a name, nominal, or pronominal phrase - which is the scope of this paper as well. One common strategy shared by (Soon et al., 2001; Ng and Cardie, 2002; Ittycheriah et al., 2003) is that a statistical model is trained to measure how likely a pair of mentions corefer; then a greedy procedure is followed to group mentions into entities. While this approach has yielded encouraging results, the way mentions are linked is arguably suboptimal in that an instant decision is made when considering whether two mentions are linked or not.</Paragraph>
    <Paragraph position="1"> In this paper, we propose to use the Bell tree to represent the process of forming entities from mentions. The Bell tree represents the search space of the coreference resolution problem - each leaf node corresponds to a possible coreference outcome. We choose to model the process from mentions to entities represented in the Bell tree, and the problem of coreference resolution is cast as finding the &amp;quot;best&amp;quot; path from the root node to leaves. A binary maximum entropy model is trained to compute the linking probability between a partial entity and a mention.</Paragraph>
    <Paragraph position="2"> The rest of the paper is organized as follows. In Section 2, we present how the Bell tree can be used to represent the process of creating entities from mentions and the search space. We use a maximum entropy model to rank paths in the Bell tree, which is discussed in Section 3. After presenting the search strategy in Section 4, we show the experimental results on the ACE 2002 and 2003 data, and the Message Understanding Conference (MUC) (MUC, 1995) data in Section 5. We compare our approach with some recent work in Section 6.</Paragraph>
  </Section>
class="xml-element"></Paper>