File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/90/c90-2049_concl.xml

Size: 2,098 bytes

Last Modified: 2025-10-06 13:56:27

<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-2049">
  <Title>Dependency Analyzer: A Knowledge-Based Approach to Structural Disambiguation</Title>
  <Section position="6" start_page="286" end_page="286" type="concl">
    <SectionTitle>
7 Concluding Remarks
</SectionTitle>
    <Paragraph position="0"> We deveh)ped the DepeT~dcrtcy Anal:/zer to re:olve structural ambiguity by sen:antic processing. It aims t&lt;~ overcome two serious problems in realizing pr:'a'tical semantic pr,~,cessing: ::en::@u'::nm:ie conslru{tion of knowledge and efficient use nf that knowledge. The key ideas, path.</Paragraph>
    <Paragraph position="1"> .sea~'ch and distance calcuiatiora, ~~e.re shown to be feasible.</Paragraph>
    <Paragraph position="2"> \Ve now have a knowledge base constructed by using defi:,.itions giver~ in the &amp;quot;IBM Dictionary of Computing/' which inch:des about 20.009 instance.s of dependency :trueturc'.s, h: addilion, we evaluated the system by disan:biguat.ing the prepositional phrase attachment of about 2,0()0 sentence.':. The results were as follows: (1) :he number of arzflJiguou:-; prepositio::al phrases wa&gt; 4.290, (2) the numbe, of correctly (lisanfi}iguat.ed a'~ta{:hm{'n:s was 3,569, and (3) the success ratio of disambiguatio:: was 83.2%.</Paragraph>
    <Paragraph position="3"> Further enhancement plans arc listed be.low: ,, ~,Y=~'. are exploring the formalization of dependency distar, ce with reference to graph theory. I)epe.ndeney distMlee is aSsllnled to be a score lbr the (:OIlSistel~cy of a dependency with tim background knowledge and context. The background knowledge and context are represented as trees (special ca.~es of graphs), and c(msistency might be defined by a degree of matching between trees.</Paragraph>
    <Paragraph position="4"> ,L. We are planning to enhance tile system for other problems such as adverb attachment and scope of eonj'unction.s. To resolve general struetmal ambiguity problems, we must design a general ambiguity-packed syntactic strncture, since the system can deal wilh locally packed ambiguities.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML