<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2106">
  <Title>Virach Sornlertlamvanich TCL, NICT Thatsanee Charoenporn TCL, NICT</Title>
  <Section position="10" start_page="832" end_page="833" type="evalu">
    <SectionTitle>
6 Evaluation through an application
</SectionTitle>
    <Paragraph position="0"> Toevaluate the proposed framework, weare building an information retrieval system. Figure 3 shows the system architecture.</Paragraph>
    <Paragraph position="1"> A user can input a topic to retrieve the documents related to that topic. A topic can consist of keywords, website URL'sand documents which describe the topic. From the topic information, the system builds a user interest model. The system then uses a search engine and a crawler to search for information related to this topic in WWW and stores the results in the local database. Generally, the search results include many noises. To filter out these noises, we build a query from the user interest model and then use this query to retrieve documents inthelocal database. Those documents similar to the query are considered as more related tothe topic and the user's interest, andare returned to the user. When the user obtains these retrieval results, he can evaluate these documents and give the feedback to the system, which is used for the further refinement of the user interest model.</Paragraph>
    <Paragraph position="2"> Language resources can contribute to improving the system performance in various ways.</Paragraph>
    <Paragraph position="3"> Query expansion is a well-known technique which expands user's queryterms intoaset ofsimilar and related terms by referring to ontologies. Our system is based on the vector space model (VSM)and traditional query expansion can be applicable using the ontology.</Paragraph>
    <Paragraph position="4"> There has been less research on using lexical in- null formation for information retrieval systems. One possibility we are considering is query expansion by using predicate-argument structures of terms.</Paragraph>
    <Paragraph position="5"> Suppose a user inputs two keywords, &amp;quot;hockey&amp;quot; and &amp;quot;ticket&amp;quot; as a query. The conventional query expansion technique expands these keywords to a set of similar words based on an ontology. By referring to predicate-argument structures in the lexicon, we can derive actions and events as well which take these words as arguments. In the above example, by referring to the predicate-argument structure of &amp;quot;buy&amp;quot; or &amp;quot;sell&amp;quot;, and knowing that these verbs can take &amp;quot;ticket&amp;quot; in their object role, we can add &amp;quot;buy&amp;quot; and &amp;quot;sell&amp;quot; to the user's query. This new type of expansion requires rich lexical information such as predicate argument structures, and the information retrieval system would be a good touchstone of the lexical information.</Paragraph>
  </Section>
class="xml-element"></Paper>