<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2419">
  <Title>Semantic Role Labeling using Maximum Entropy Model</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The semantic role represents the relationship between a predicate and an argument. It provides a general semantic interpretation of the sentence, and it can play a key role in NLP. The shared task of CoNLL-2004 concerns the automatic semantic role labeling (Carreras, 2004). The challenge for this task is to come forward with machine learning approaches which based on only partial syntactic information such as words, POS tags, chunks, clauses, and named entities.</Paragraph>
    <Paragraph position="1"> Some machine learning approaches for semantic role labeling have been previously developed (Gildea, 2002; Pradhan, 2003; Thompson, 2003). Gildea (2002) proposed a probabilistic discriminative model to assign a semantic roles to the constituent. However, it needs a complex interpolation for smoothing because of the data sparseness problem. Pradhan (2003) applied a support vector machine to semantic role labeling, but if it use a polynomial kernel function for the dependencies between features, it requires high computational complexity. Futhermore, becuase the SVM is a binary classifier, one-vs-rest or pairwise method is required for multi-class classification. Thompson (2003) proposed a probabilistic generative model which the constituents is generated by the semantic roles. In this model, because a constituent depends only on the role that generated it, and constituents are independent of each other, so this model can not utilize contextual information or a relational information between the constituent and the predicate.</Paragraph>
    <Paragraph position="2"> In this paper, we propose a semantic role labeling method using a maximum entropy model. It is motivated by the thought of that for building a successful model, some knowledge of the task are reflected into the model based on the machine learning technique. In this method, we try to combine the structural linguistic knowledge linking syntax to semantics into the machine learning technique. It is realized in terms of two aspects: one is the model framework, the other is the design of feature sets. First of all, for the model framework, we utilize the syntactic knowledge of representing the semantic roles in a clause: the arguments of a predicate are located in the immediate clause or the upper clauses. Secondly, for the feature sets, we consider the relation between syntactic and semantic characteristics of a given context. For implementing the method with a machine learning algorithm, we take a maximum entropy model, which enables not only to exploit rich features but also to alleviate the data sparseness problem in a well-founded model.</Paragraph>
    <Paragraph position="3"> The remaining of the paper is organized as follows: section 2 describes the proposed semantic role labeling method using a maximum entropy model. Section 3 presents feature sets for semantic role labeling. Section 4 shows some experimental results of the proposed method.</Paragraph>
    <Paragraph position="4"> Finally, section 5 concludes with some directions of future works.</Paragraph>
  </Section>
class="xml-element"></Paper>