<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-1029">
  <Title>Scaling up from Dialogue to Multilogue: some principles and benchmarks</Title>
  <Section position="3" start_page="0" end_page="231" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The development of dialogue systems in which a human agent interacts using natural language with a computational system is by now a flourishing domain (see e.g.</Paragraph>
    <Paragraph position="1"> (NLE, 2003)), buttressed by an increasing theoretical and experimental literature on the properties of dialogue (see e.g. recent work in the SEMDIAL and SIGDIAL conferences). In contrast, the development of multilogue systems, in which conversation with 3 or more participants ensue--is still in its early stages, as is the theoretical and experimental study of multilogue. The fundamental issue in tackling multilogue is: how can mechanisms motivated for dialogue (e.g. information states, protocols, update rules etc) be scaled up to multilogue? In this paper we extract from a conversational corpus, the British National Corpus (BNC), several benchmarks that characterize dialogue and multilogue interaction. These are based on the resolution possibilities of non-sentential utterances (NSUs). We then use these benchmarks to evaluate certain general transformations whose application to a dialogue interaction system yield a system appropriate for multilogue.</Paragraph>
    <Paragraph position="2"> There are of course various plausible views of the relation between dialogue and multilogue. One possible approach to take is to view multilogue as a sequence of dialogues. Something like this approach seems to be adopted in the literature on communication between autonomous software agents. However, even though many situations considered in multiagent systems do involve more than two agents, most interaction protocols are designed only for two participants at a time. This is the case of the protocol specifications provided by FIPA (Foundation for Intelligent Physical Agents) for agent communication language messages (FIPA, 2003). The FIPA interaction protocols (IP) are most typically designed for two participants, an initiator and a responder . Some IPs permit the broadcasting of a message to a group of addressees, and the reception of multiple responses by the original initiator (see most particularly the Contract Net IP). However, even though more than two agents participate in the communicative process, as (Dignum and Vreeswijk, 2003) point out, such conversations can not be considered multilogue, but rather a number of parallel dialogues.</Paragraph>
    <Paragraph position="3"> The Mission Rehearsal Exercise (MRE) Project (Traum and Rickel, 2002), one of the largest multilogue systems developed hitherto, is a virtual reality environment where multiple partners (including humans and other autonomous agents) engage in multi-conversation situations. The MRE is underpinned by an approach to the modelling of interaction in terms of obligations that different utterance types bring about originally proposed for dialogue (see e.g. (Matheson et al. , 2000)). In particular, this includes a model of the grounding process (Clark, 1996) that involves recognition and construction of common ground units (CGUs) (see (Traum, 2003)).</Paragraph>
    <Paragraph position="4"> Modelling of obligations and grounding becomes more complex when considering multilogue situations. The model of grounding implemented in the MRE project can only be used in cases where there is a single initiator and responder. It is not clear what the model should be for  multiple addressees: should the contents be considered grounded when any of the addressees has acknowledged them? Should evidence of understanding be required from every addressee? Since their resolution is almost wholly reliant on context, non sentential utterances provide a large testbed concerning the structure of both dialogue and multilogue. In section 2 we present data from the British National Corpus (BNC) concerning the resolution of NSUs in dialogue and multilogue. The main focus of this data is with the distance between antecedent and fragment. We use this to extract certain benchmarks concerning multilogue interaction. Thus, acknowledgement and acceptance markers (e.g. 'mmh', 'yeah') are resolved with reference to an utterance (assertion) which they ground (accept). The data we provide shows that acknowledgements in multilogue, as in dialogue, are adjacent to their antecedent. This provides evidence that, in general, a single addressee serves to signal grounding. In contrast, BNC data indicates the prevalence in multilogue of short answers that are resolved using material from an antecedent question located several turns back, whereas in dialogue short answers are generally adjacent to their antecedent. This provides evidence against reducing querying interaction in multilogue to a sequence of dialogues. We show that long distance short answers are a stable phenomenon for multilogue involving both small ([?]5 persons) and large (&gt; 5 persons) groups, despite the apparently declining interactivity with increasing group size flagged in experimental work (see (Fay et al., 2000)).</Paragraph>
    <Paragraph position="5"> In section 3 we sketch the basic principles of issue based dialogue management which we use as a basis for our subsequent investigations of multilogue interaction. This will include information states and formulation of protocols for querying and assertion in dialogue. In section 4 we consider three possible transformations on dialogue protocols into multilogue protocols. These transformations are entirely general in nature and could be applied to protocols stated in whatever specification language. We evaluate the protocols that are generated by these transformations with reference to the benchmarks extracted in section 2. In particular, we show that one such transformation, dubbed Add Side Participants(ASP), yields protocols for querying and assertion that fulfill these benchmarks. Finally, section 5 provides some conclusions and pointers to future work.</Paragraph>
  </Section>
class="xml-element"></Paper>