<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1058">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Word sense disambiguation (WSD) has been a hot topic in natural language processing, which is to determine the sense of an ambiguous word in a specific context. It is an important technique for applications such as information retrieval, text mining, machine translation, text classification, automatic text summarization, and so on. Statistical solutions to WSD acquire linguistic knowledge from the training corpus using machine learning technologies, and apply the knowledge to disambiguation. The first statistical model of WSD was built by Brown et al. (1991).</Paragraph>
    <Paragraph position="1"> Since then, most machine learning methods have been applied to WSD, including decision tree, Bayesian model, neural network, SVM, maximum entropy, genetic algorithms, and so on. For different learning methods, supervised methods usually achieve good performance at a cost of human tagging of training corpus. The precision improves with larger size of training corpus.</Paragraph>
    <Paragraph position="2"> Compared with supervised methods, unsupervised methods do not require tagged corpus, but the precision is usually lower than that of the supervised methods. Thus, knowledge acquisition is critical to WSD methods.</Paragraph>
    <Paragraph position="3"> This paper proposes an unsupervised method based on equivalent pseudowords, which acquires WSD knowledge from raw corpus. This method first determines equivalent pseudowords for each ambiguous word, and then uses the equivalent pseudowords to replace the ambiguous word in the corpus. The advantage of this method is that it does not need parallel corpus or seed corpus for training. Thus, it can use a large-scale monolingual corpus for training to solve the data-sparseness problem. Experimental results show that our unsupervised method performs better than the supervised method.</Paragraph>
    <Paragraph position="4"> The remainder of the paper is organized as follows. Section 2 summarizes the related work.</Paragraph>
    <Paragraph position="5"> Section 3 describes the conception of Equivalent Pseudoword. Section 4 describes EP-based Unsupervised WSD Method and the evaluation result. The last section concludes our approach.</Paragraph>
  </Section>
class="xml-element"></Paper>