<?xml version="1.0" standalone="yes"?>
<Paper uid="P85-1026">
  <Title>REPAIRING REFERENCE IDENTIFICATION FAILURES BY RELAXATION</Title>
  <Section position="7" start_page="215" end_page="216" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> Our goal m thls work Is to budd robust natural language understanding systems, allowmg them to detect and avold mlscommunlcatlon. The goal is not to make a perfect listener but a more tolerant one that could avold many mistakes, though still wrong on occasion. In Section 2, we mtroduced a taxonomy of mlscommunlcatlon problems that occur tn expert apprentice dialogues. We showed that reference mistakes are one kind of obstacle to robust communication. To tackle reference problems, we descrlbed how to extend the succeed/fad paradigm followed by previous natural language researchers We represented real world objects hlerarchlcallv in a knowledge base using a representation language, KL-One. that follows in the tradition of semantlc networks and frames. In such a representatlon framework, the reference identification task looks for a referent by comparing the representation of the speakers Input to elements in the knowledge base by using a matching procedure. Failure to find a referent in previous reference identlhcatlon systems resulted In the unsuccessful termination of the reference task We claim that people behave better than this and exphcltly illustrated such cases in an expert-apprentlce domain about toy water pumps.</Paragraph>
    <Paragraph position="1"> We developed a theory of relaxation for recovering from reference failures that provides a much better model for human performance. When people are asked to identify objects, they go about it m a certain way. flnd candidates, adjust as necessary, re-try, and, if necessary, glve up and ask for help. We claim that relaxation is an Integral part of this process and that the particular parameters of relaxation differ from task to task and person to person. Our work models the relaxation process and provldes a computatlonal model for experimenting w~th the different parameters. The theory incorporates the same language and physical knowledge that people use m performing reference identification to guide the relaxation process. Thls knowledge Is represented as a set of rules and as data m a hierarchical knowledge base. Rule-based relaxation provided a methodical way to use knowledge about language and the world to find a referent. The hlererchxcal representation made It posslble to tackle issues of Impreclslon and over-specification In a speakers description. It allows one to check the position of a description in the hierarchy and to use that position to fudge Imprecision and over-speclfication and to suggest possible repairs to the descriptlon.</Paragraph>
    <Paragraph position="2">  Interestingly. one would expect that &amp;quot;closest&amp;quot; match would suffice to solve the problem of finding a referent. We showed, however, that it doesn't usually provide you with the correct referent. Closest match isn't sufficient because there are many features associated wlth an object and, thus. determimng whlch of those features to keep and which to drop Is a difficult problem due to the combinatorlcs and the effects of context. The relaxation method described circumvents the problem by using the knowledge that people have about language and the physical world to prune down the search space.</Paragraph>
  </Section>
class="xml-element"></Paper>