<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1041">
  <Title>Sense Disambiguation Using Semantic Relations and Adjacency Information</Title>
  <Section position="3" start_page="293" end_page="293" type="intro">
    <SectionTitle>
2 Previous Work on Disambiguation
</SectionTitle>
    <Paragraph position="0"> In computational linguistics, considerable effort has been devoted to word-sense disambiguation \[8\]. These approaches can be broadly classified based on the reference from which senses are assigned, and on the method used to take the context of occurrence into account. The references have ranged from detailed custom-built lexicons (e.g., \[l 1\]) to standard resources like dictionaries and thesauri like Roget's (e.g., \[2, 10, 14\]). To take the context into account, researchers have used a variety of statistical weighting and spreading activation models (e.g., \[9, 14, 15\]). This section gives brief descriptions of some approaches that use on-line dictionaries and WordNet as references.</Paragraph>
    <Paragraph position="1"> WordNet is a large, manually-constructed semantic network built at Princeton University by George Miller and his colleagues \[12\]. The basic unit of WordNet is a set of synonyms, called a synset, e.g., \[go, travel, move\]. A word (or a word collocation like &amp;quot;operating room&amp;quot;) can occur in any number of synsets, with each synset reflecting a different sense of the word. WordNet is organized around a taxonomy of hypernyms (A-KIND-OF relations) and hyponyms (inverses of A-KIND-OF), and 10 other relations. The disambiguation algorithm described by Voorhees \[16\] partitions WordNet into hoods, which are then used as sense categories (like dictionary subject codes and Roget's thesaurus classes). A single synset is selected for nouns based on the hood overlap with the surrounding text.</Paragraph>
    <Paragraph position="2"> The research on extraction of semantic relations from dictionary definitions (e.g., \[5, 7\]) has resulted in new methods for disambiguation, e.g., \[2, 15\]. For example, Vanderwende \[15\] uses semantic relations extracted from LDOCE to interpret nominal compounds (noun sequences). Her algorithm disambiguates noun sequences by using the dictionary to search for pre-defined relations between the two nouns; e.g., in the sequence &amp;quot;bird sanctuary,&amp;quot; the correct sense of&amp;quot;sanctuary&amp;quot; is chosen because the dictionary definition indicates that a sanctuary is an area for birds or animals.</Paragraph>
    <Paragraph position="3"> Our algorithm, which is described in the next section, is in the same spirit as Vanderwende's but with two main differences. In addition to noun sequences, the algorithm has heuristics for handling 11 other adjacency relationships. Second, the algorithm brings to bear both WordNet and semantic relations extracted from an on-line Webster's dictionary during disambiguation.</Paragraph>
  </Section>
class="xml-element"></Paper>