<?xml version="1.0" standalone="yes"?>
<Paper uid="P95-1041">
  <Title>Sense Disambiguation Using Semantic Relations and Adjacency Information</Title>
  <Section position="4" start_page="293" end_page="294" type="metho">
    <SectionTitle>
3 Sense Disambiguation with
Adjacency Information
</SectionTitle>
    <Paragraph position="0"> The input to the disambiguator is a pair of words, along with the adjacency relationship that links them in the input text. The adjacency relationship is obtained automatically by processing the text through the Xerox PARC part-of-speech tagger \[6\] and a phrase extractor.</Paragraph>
    <Paragraph position="1"> The 12 adjacency relationships used by the disambiguator are listed below. These adjacency relationships were derived from an analysis of captions of news photographs provided by the Associated Press. The examples from the captions also helped us identify the heuristic rules necessary for automatic disambiguation using WordNet and the Webster's dictionary. In the table below, each adjacency category is accompanied by an example. 39 heuristic rules are used currently.</Paragraph>
    <Paragraph position="2">  Noun that is at the head of a Sentenced to life prepositional phrase following a verb Nouns that are subject and The hawk found a object of the same action perch Given a pair of words and the adjacency relationship, the disambiguator applies all heuristics corresponding to that category, and those word senses that are rejected by all heuristics are discarded. Due to space considerations, we will not describe the heuristic rules individually but  instead identify some common salient features. The heuristics are described in detail in \[3\].</Paragraph>
    <Paragraph position="3"> * Several heuristics look for a particular semantic relation like hypernymy or purpose linking the two input words, e.g., &amp;quot;return&amp;quot; is a hypernym of &amp;quot;forehand.&amp;quot; * Many heuristics look for particular semantic relations linking the two input words to a common word or synset; e.g., a &amp;quot;church&amp;quot; and a &amp;quot;home&amp;quot; are both buildings.</Paragraph>
    <Paragraph position="4"> * Many heuristics look for analogous adjacency patterns either in dictionary definitions or in example sentences, e.g., &amp;quot;write a mystery&amp;quot; is disambiguated by analogy to the example sentence &amp;quot;writes poems and essays.&amp;quot; * Some heuristics look for specific hypernyms such as person or place in the input words; e.g., if a noun is followed by a proper name (as in &amp;quot;tenor Luciano Pavarotti&amp;quot; or &amp;quot;pitcher Curt Schilling&amp;quot;), those senses of the noun that have &amp;quot;person&amp;quot; as a hypernym are chosen.</Paragraph>
    <Paragraph position="5"> The disambiguator has been used in two retrieval programs, ImEngine, a program for semantic retrieval of image captions, and NetSerf, a program for finding Internet information archives \[3, 4\]. The initial results have not been promising, with both programs reporting deterioration in performance when the disambiguator is included. This agrees with the current wisdom in the IR community that unless disambiguation is highly accurate, it might not improve the retrieval system's performance \[ 13\].</Paragraph>
  </Section>
class="xml-element"></Paper>