<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2028">
  <Title>Using Lexical Dependency and Ontological Knowledge to Improve a Detailed Syntactic and Semantic Tagger of English</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Part-of-speech (POS) tagging has been one of the fundamental areas of research in natural language processing for many years. Most of the prior research has focussed on the task of labeling text with tags that reflect the words' syntactic role in the sentence. In parallel to this, the task of word sense disambiguation (WSD), the process of deciding in which semantic sense the word is being used, has been actively researched. This paper addresses a combination of these two fields, that is: labeling running words with tags that comprise, in  additiontotheirsyntacticfunction,abroadsemantic class that signifies the semantics of the word in the context of the sentence, but does not necessarily provide information that is sufficiently fine-grained as to disambiguate its sense. This differs [?]National Institute of Information and Communications Technology +ATR Spoken Language Communication Research Labs from what is commonly meant by WSD in that although each word may have many &amp;quot;senses&amp;quot; (by senses here, we mean the set of semantic labels the word may take), these senses are not specific to the word itself but are drawn from a vocabulary applicable to the subset of all types in the corpus that may have the same semantics.</Paragraph>
    <Paragraph position="1"> In order to perform this task, we draw on research from several related fields, and exploit publicly available linguistic resources, namely the WordNet database (Fellbaum, 1998). Our aim is to simultaneously disambiguate the semantics of the words being tagged while tagging their POS syntax. We treat the task as fundamentally a POS tagging task, with a larger, more ambiguous tag set. However, as we will show later, the 'n-gram' feature set traditionally employed to perform POS tagging, while basically competent, is not up to this challenge, and needs to be augmented by features specifically targeted at semantic disambiguation. null</Paragraph>
  </Section>
class="xml-element"></Paper>