<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1018">
  <Title>Some Notes on the Complexity of Dialogues *</Title>
  <Section position="8" start_page="167" end_page="168" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> -The project VALDIA has produced useful insights into the complexity of dialogue: Spoken dialogue is very complex! Exhaustive testing of a DM is for some scenarios/dialogue models impossible. The results were obtained during the development of a test program for a DM.</Paragraph>
    <Paragraph position="1"> Purpose of the testing was to be able to integrate a DM into the dialogue system which contained as few errors as possible. We would like to highlight the following points: * VALDIA has proven its usefulness in that it is able to detect errors in the implementation of DMs before', it is integrated into the complete dialogue system. During the testing we encountered, in addition to logical bugs, errors which would never be detected during normal testing with the complete dialogue system.</Paragraph>
    <Paragraph position="2"> * By including the automata into Vm.,-DIA it is possible to concentrate the testing on &amp;quot;interesting utterance sequences&amp;quot; and, despite the huge universe of theoretically possible dialogues, obtain a status of the DM which for certain tasks is well tested.</Paragraph>
    <Paragraph position="3"> It is simple to adapt for the testing of a new DM. Technically the only thing that has to changed is the definition/constraints of the definition utterances. This is at present a semi-automatic process. Conceptually the automata has to be defined, unless one wants to test in Monte Carlo mode.</Paragraph>
    <Paragraph position="4"> In the current implementation VALDIA uses about 10% of the processing time compared to the DM. Thus VALDIA can control between 5 and 10 instances of the DM depending on available resources in the net.</Paragraph>
    <Paragraph position="5"> VALDIA is platform independent. At our site, we are using a mixture of different types of computers, both PCs running under Windows/Linux and UNIX machines. Depending on load, we are flexible to utilize any of the free resources for the testing.</Paragraph>
    <Paragraph position="6"> We are currently in the process of adapting VALDIA for a new scenario. For this DM input consists of grammatical structures, rather than sets of semantic objects. Since the VALDIA project started, interesting research results have emerged and there are lot of things that remain to be done. Amongst those, we will pay attention to at least the following topics: null The current implementation of VALDIA has no means of react on the output from the DM. For intelligent testing this has to be incorporated into the system. Possible future directions are described in (Eckert et al., 1998), (Schefiler and Young, 2000) and (Lin and Lee, 2000). In, e.g., (Eckeft et al., 1998) VALDIA is replaced by an simulated user, and the authors describe a statistical method for reacting on system responses.</Paragraph>
    <Paragraph position="7">  * We have to develop a tool for semi-automatically anaJyzing the trace files produced by VALDIA. Possible future features are just saving the files of those dialogues/utterances which resulted in an error.</Paragraph>
  </Section>
class="xml-element"></Paper>