<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-1606">
  <Title>Generating Referential Descriptions Under Conditions of Uncertainty</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we have presented an approach for generating referential descriptions under conditions of uncertainty. The approach combines a proper recognition of objects associated with some degree of uncertainty, as well as identification through a repair mechanism, motivated by the need to identify objects even for descriptions that originally appear uninterpretable. On these lines, we have reinterpreted concepts of algorithms generating referring expressions in view of uncertainties about the appearance of objects.</Paragraph>
    <Paragraph position="1"> Incorporating measures of uncertainty in such an algorithm attacks strong assumptions and effects underlying most of the existing algorithms: * They typically require crisp specifications concerning attribution of descriptors to referents and knowledge of the audience. Especially the connection to modern user models may require coarse-grained interpretations here.</Paragraph>
    <Paragraph position="2"> * A single result is produced even if several reasonable variants exist, and this choice is implicitly determined by the preference ordering imposed on the descriptors.</Paragraph>
    <Paragraph position="3"> * The interaction with other components of an NL generation system and an embedding dialog system is rather limited. Reference generation is typically conceived as a pure functional service, with no feedback, taking into account syntactic constraints, at best (e.g., [Horacek 1997]). An embedding dialog system has no chance to find out possible sources for an identification failure.</Paragraph>
    <Paragraph position="4"> The algorithm incorporating measures to deal with uncertainties provides facilities to improve this situation: * Specifications concerning attribution of descriptors to referents and knowledge of the audience can be done in a direct fashion, requiring no interpretations.</Paragraph>
    <Paragraph position="5"> * There are some parameters to control the choice of descriptors, the conciseness and expected effectiveness of the result, including an afterwards optimization which only requires re-calculation of probabilities.</Paragraph>
    <Paragraph position="6"> * The probabilities of identification associated with the intended referents and those potential distractors that fall under the repair facility give an indication about the likelihood of success of the identification task and also about potential sources for a failure. Moreover, the situation about probabilities and descriptors may suggest variants in building surface expressions, such as putting emphasis on a critical descriptor.</Paragraph>
  </Section>
class="xml-element"></Paper>