<?xml version="1.0" standalone="yes"?>
<Paper uid="W98-0612">
  <Title>Exemplar-Based Sense Modulation</Title>
  <Section position="4" start_page="89" end_page="90" type="metho">
    <SectionTitle>
4. Implemented Prototype
</SectionTitle>
    <Paragraph position="0"> The implemented system is structured in two marker passing networks. The bottom network, the ontology network, serves as the system knowledge base to define concepts in the second network. This definition includes concept properties and relationships between concepts.</Paragraph>
    <Paragraph position="1"> We used Mikrokosmos ontology (Mahesh &amp; Nirenburg, 1995).</Paragraph>
    <Paragraph position="2"> The second network, the lexicon network, consists of four layers of nodes. Figure 3 displays the schematic structure of the lexicon network. Lexemes, (displayed as squares) appear at the bottom. Connected to lexemes are concepts (rounded rectangles). Concepts are connected exemplars (double-lined rectangles). Exemplars constst of a number of sense-concepts (occurrences of concepts in exemplars). Associated with each sense-concept is a sense-view (displayed as banners).</Paragraph>
    <Paragraph position="3">  The process begins when input words are looked up the in ontology and their corresponding lexemes are found. Concepts connected to these lexemes are then activated which, in turn, leads to activation of all exemplars in which input words appear.</Paragraph>
    <Paragraph position="4"> Exemplars activated for a word, or more precisely, for the word's associated concepts, represent the model's knowledge, up to that point, of various ways that the input word can interact with other words.</Paragraph>
    <Paragraph position="5"> In the implemented system, determining adaptability is carried out simultaneously and concurrently by individual exemplars triggered by input words. Attached to each exemplars (in fact, attached to a .group of exemplars with sirnilar context) is an agent. Agents, (implemented as Java TM threads) receive activation and individually start measuring the adaptability of their exemplars with the input. More details can be found in Rais-Ghasem (1998).</Paragraph>
  </Section>
  <Section position="5" start_page="90" end_page="90" type="metho">
    <SectionTitle>
5. Experiments
</SectionTitle>
    <Paragraph position="0"> This section presents more examples of output generated by the implemented prototype. These examples intend to underline different aspects of the proposed model.</Paragraph>
    <Section position="1" start_page="90" end_page="90" type="sub_section">
      <SectionTitle>
5.1 Sense-View Development
</SectionTitle>
      <Paragraph position="0"> This experiment provides another example of sense-view development. The destination senseview, initially exemplified by only one exemplar: Mary went to the office.</Paragraph>
      <Paragraph position="1"> This is how this sense-view looks like at this</Paragraph>
    </Section>
    <Section position="2" start_page="90" end_page="90" type="sub_section">
      <SectionTitle>
Notice both IsKindOf-Building and IsKindOf-
</SectionTitle>
      <Paragraph position="0"> Place are relatively central to office and therefore to this sense-view. The above set shrinks rapidly after processing the next input: The student went to the stadium.</Paragraph>
      <Paragraph position="1">  Here, unlike previous case, IsKindOf-Place is more prominent than IsKindOf-Building. This is because park is not a building, but nonetheless, its effect is not enough to completely eliminate IsKindOf-Building from the sense-view. The next input, however, strengthens IsKindOf-Building and weakens IsKindOf-Place, mainly because this property is not immediately present for auditorium.</Paragraph>
      <Paragraph position="2"> The musician went to the auditorium.</Paragraph>
    </Section>
    <Section position="3" start_page="90" end_page="90" type="sub_section">
      <SectionTitle>
5.2 Property Highlighting/Backgrounding
</SectionTitle>
      <Paragraph position="0"> This experiment provides further evidence on how a single concept in this model can be viewed from different perspectives. Notice how the generated output for book changes in each of the following cases.</Paragraph>
      <Paragraph position="1"> The book broke the window.</Paragraph>
      <Paragraph position="2">  The student read the book.</Paragraph>
      <Paragraph position="3"> This is also a case of lexical disambiguation, or sense selection: read could mean announce or study for an academic degree.</Paragraph>
    </Section>
    <Section position="4" start_page="90" end_page="90" type="sub_section">
      <SectionTitle>
5.3 Property Promotion/Demotion
</SectionTitle>
      <Paragraph position="0"> This experiment provides an example of how one concept appearing in a context can be associated with properties not necessarily present in its original representation. Here is the input context: Mary reads physics.</Paragraph>
      <Paragraph position="1"> Because of its appearance in this context, MaD' (in fact, its corresponding concept, Female-Human) will be depicted as student. In other words, through the assigned sense-view, properties specific to student (e.g., being a social/academic role) will be associated with Mary in this context. The experiment also provides another example of the system's lexical disambiguation ability (read is ambiguous). Here is the output word sense for</Paragraph>
    </Section>
    <Section position="5" start_page="90" end_page="90" type="sub_section">
      <SectionTitle>
5.4 Multiple Word Senses
</SectionTitle>
      <Paragraph position="0"> There are cases in which context does not favor any of the alternative readings of a word, and therefore the ambiguity must be maintained in the output. This experiment demonstrates the system's ability to handle such cases. In this example, both readings of bank are compatible, to some degree, with the destination sense-view.</Paragraph>
      <Paragraph position="1"> John went to the bank.</Paragraph>
      <Paragraph position="2"> Here is the output word sense for bank, with two sense-concepts, both linked to the same senseview. null</Paragraph>
    </Section>
    <Section position="6" start_page="90" end_page="90" type="sub_section">
      <SectionTitle>
5.5 Instantiation of General Terms
</SectionTitle>
      <Paragraph position="0"> This last experiment is inspired by the experiment conducted by Anderson et al.</Paragraph>
      <Paragraph position="1"> (1976). These researchers found that shark was a better cue than fish for subjects in remembering a sentence like the following: The fish attacked the man.</Paragraph>
      <Paragraph position="2"> They concluded thatfish was instantiated to, and encoded accordingly as, shark in the subjects' memory.</Paragraph>
      <Paragraph position="3"> Here is the word sense generated for fish in the above context. Notice how in the output, fish is associated with properties specific to shark (aggressiveness and black color).</Paragraph>
      <Paragraph position="4">  Finally, here is an example of how sense-views can be used to establish some properties about unknown words. Here is the input: Mary went to the palladium.</Paragraph>
      <Paragraph position="5"> The word palladium is not defined in the lexicon. Nevertheless, the system associates it with the proper sense-view. Through this senseview, some initial properties for palladium can be inferred.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>