<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0838">
  <Title>SenseLearner: Minimally Supervised Word Sense Disambiguation for All Words in Open Text</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"> For some natural language processing tasks, such as part of speech tagging or named entity recognition, regardless of the approach considered, there is a consensus on what makes a successful algorithm (Resnik and Yarowsky, 1997). Instead, no such consensus has been reached yet for the task of word sense disambiguation, and previous work has considered a range of knowledge sources, such as local collocational clues, membership in a semantically or topically related word class, semantic density, etc. Other related work has been motivated by the intuition that syntactic information in a sentence contains enough information to be able to infer the semantics of words. For example, according to (Gomez, 2001), the syntax of many verbs is determined by their semantics, and thus it is possible to get the later from the former. On the other hand, (Lin, 1997) proposes a disambiguation algorithm that relies on the basic intuition that if two occurrences of the same word have identical meanings, then they should have similar local context. He then extends this assumption one step further and proposes an algorithm based on the intuition that two different words are likely to have similar meanings if they occur in an identical local context.</Paragraph>
  </Section>
class="xml-element"></Paper>