<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0201">
  <Title>Synchronization in an Asynchronous Agent-based Architecture for Dialogue Systems</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> More and more people are building dialogue systems. Architecturally, these systems tend to fall into two camps: those with pipelined architectures (e.g., (Lamel et al., 1998; Nakano et al., 1999)), and those with agent-based architectures (e.g., (Senefi et al., 1999; Stent et al., 1999; Rudnicky et al., 1999)). Agent-based architectures are advantageous because they free up system components to potentially act in a more asynchronous manner. However, in practice, most dialogue systems built on an agent-based architecture pass messages such that they are basically functioning in terms of a pipelined ow-of-information.</Paragraph>
    <Paragraph position="1"> Our original implementation of the TRIPS spoken dialogue system (Ferguson and Allen, 1998) was such an agent-based, pipelined ow-of-information system. Recently, however, we made changes to the system (Allen et al., 2001a) which allow it to take advantage of the distributed nature of an agent-based system. Instead of system components passing information in a pipelined manner (interpretation ! discourse management ! generation), we allow the subsystems of interpretation, behavior (reasoning and acting) and generation to work asynchronously. This makes the TRIPS system truly distributed and agent-based.</Paragraph>
    <Paragraph position="2"> Thedrivingforcesbehindthesechangesare to provide a framework for incremental and asynchronous language processing, and to allow for a mixed-initiative system at the task level. We describe these motivations brie y here.</Paragraph>
    <Paragraph position="3"> Incremental Language Processing In a pipelined (or pipelined ow-of-information) system, generation does not occur until afterboththeinterpretationandreasoningpro- null cesses have completed. This constraint is not present in human-human dialogue as evidenced by the presence of grounding, utterance acknowledgment, and interruptions.</Paragraph>
    <Paragraph position="4"> Making interpretation, behavior, and generation asynchronous allows, for example, the system to acknowledge a question while it is still working on flnding the answer.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Mixed-initiative Interaction Although
</SectionTitle>
      <Paragraph position="0"> pipelined systems allow the system to take discourse-level initiative (cf. (Chu-Caroll and Brown, 1997)), it is di-cult to see how they could allow the system to take task-level initiative in a principled way. In most systems, reasoning and action are driven mostly by interpreted input (i.e., they are reactive to the user's utterances). In a mixed-initiative system, the system's response should be determinednotonlybyuserinput, butalsosystem goals and obligations, as well as exogenous Philadelphia, July 2002, pp. 1-10. Association for Computational Linguistics. Proceedings of the Third SIGdial Workshop on Discourse and Dialogue, events. For example, a system with an asynchronous behavior subsystem can inform the user of a new, important event, regardless of whether it is tied to the user's last utterance.</Paragraph>
      <Paragraph position="1"> On the other hand, in the extreme version of pipelined ow-of-control, behavior cannot do anything untiltheusersayssomething, which is the only way to get the pipeline owing.</Paragraph>
      <Paragraph position="2"> The reasons for our changes are described in further detail in (Allen et al., 2001a). In this paper, we focus on the issues we encountered in developing an asynchronous agentbaseddialoguesystemandtheirrespectiveso- null lutions, whichturnouttobehighlyrelatedto the process of grounding.</Paragraph>
      <Paragraph position="3"> We flrst describe the general TRIPS architectureandinformation owandthendiscuss the various points of synchronization within the system. We then discuss what these issues mean in general for the implementation of an asynchronous agent-based system.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>