<?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="4" start_page="0" end_page="215" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> Our work is a synthesis of POS tagging and WSD, and as such, research from both these fields is directly relevant here.</Paragraph>
    <Paragraph position="1"> The basic engine used to perform the tagging in these experiments is a direct descendent of the maximum entropy (ME) tagger of (Ratnaparkhi, 1996) which in turn is related to the taggers of (Kupiec, 1992) and (Merialdo, 1994). The ME approach is well-suited to this kind of labeling because it allows the use of a wide variety of features without the necessity to explicitly model the interactions between them.</Paragraph>
    <Paragraph position="2"> The literature on WSD is extensive. For a good overview we direct the reader to (Nancy and Jean, 1998). Typically, the local context around the  word to be sense-tagged is used to disambiguate the sense (Yarowsky, 1993), and it is common for linguistic resources such as WordNet (Li et al., 1995; Mihalcea and Moldovan, 1998; Ramakrishnan and Prithviraj, 2004), or bilingual data (Li and Li, 2002) to be employed as well as more long-range context. An ME-system for WSD that operates on similar principles to our system (Suarez, 2002) was based on an array of local features that included the words/POS tags/lemmas occurring in a window of +/-3 words of the word being disambiguated. (Lamjiri et al., 2004) also developed an ME-based system that used a very simple set of features: the article before; the POS before and after; the preposition before and after, and the syntactic category before and after the word being labeled. The features used in both of these approaches resemble those present in the feature set of a standard n-gram tagger, such as the one used as the baseline for the experiments in this paper. The semantic tags we use can be seen as a form of semantic categorization acting in a similar manner to the semantic class of a word in the system of (Lamjiri et al., 2004). The major difference is that with a left-to-right beam-search tagger, labeledcontexttotherightofthewordbeinglabeled null is not available for use in the feature set.</Paragraph>
    <Paragraph position="3"> AlthoughPOStaginformationhasbeenutilized in WSD techniques (e.g. (Suarez, 2002)), there has been relatively little work addressing the problem of assigning a part-of-speech tag to a word together with its semantics, despite the fact that the tasks involve a similar process of label disambiguation for a word in running text.</Paragraph>
  </Section>
class="xml-element"></Paper>