<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1430">
  <Title>From Context to Sentence Form</Title>
  <Section position="2" start_page="0" end_page="225" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> When generating utterances, humans may choose among a number of alternative sentence forms expressing the same propositional content. Consider the following examples:  1. Amanda Huggenkiss proposes to meet you to talk about 'agents'.</Paragraph>
    <Paragraph position="1"> 2. Amanda Huggenkiss, she proposes to meet you to talk about 'agents'.</Paragraph>
    <Paragraph position="2"> 3. 'Agents' is proposed as a subject for a meeting, by Amanda Huggenkiss.</Paragraph>
    <Paragraph position="3">  Discourse pragmatics research, mainly in view of NL understanding, reveals a loose coupling between a range of grammatical markers (morpho-syntax, word order and also prosody) and difficult to verify mental categories such as 'given' and 'new'. While unpredictability seems an inherent property of pragmatic phenomena (Verschueren, 1995) we want to experimentally introduce the observed variability in an NLG device to investigate its communicative effect. Our practical goal is to enhance the effectiveness of a wearable device that provides spoken advice to a user operating in a real-world physical environment. Given a particular pragmatic context, one or another formulation is more appropriate w.r.t. communicative success (Hovy, 1990). We focus on the hearer's context (as perceived by the speaker). Like Klabunde and Jansche (1998), we are interested in linguistic form variations related to informalion</Paragraph>
    <Paragraph position="5"> packaging (Lambrecht, 1994) as an important aspect of addressee tuning. Taking into account multiple context dimensions acquired in real-time distinguishes our approach, also from other NLG research concerned with user adaptation, where only discourse and/or user profile are considered (e.g.</Paragraph>
    <Paragraph position="6"> (Krahmer and Theune, 1998; Paris, 1988)) or time and space from a linguistic-theoretical perspective (Maybury, 1991).</Paragraph>
    <Paragraph position="7"> The work reported here is part of the COMRIS I project. In an information-rich situation (e.g. when visiting a conference), a user receives relevant advice (e.g. about interesting talks, interesting persons in the neighbourhood) from her 'parrot' (see figure 1)2.</Paragraph>
    <Paragraph position="8"> Related research issues in COMRIS are physical context sensing and information focusing through agents' competition for the attention of the user (Van de Velde et al., 1998). Context-sensitive text generation contributes to the latter and depends on the fomaer. We earlier investigated how context determines the text generation process at the level of word choice (Geldof, 1999b). We proposed a multi-dimensional context model, encompassing discourse  n e context attention information g~arnmar model space structure</Paragraph>
    <Paragraph position="10"> history, physical context and user profile (Geldof, 1999a). Real-time information about these different perspectives annotates the input structure of the template-based NLG component. We use TG/2, a rule-based engine that covers the continuum between templates and syntactic generation (Busemann, 1996). Making abstraction from planning and multi-sententional discourse phenomena allows us to focus on the subject of our research: context sensitivity and surface form. In this paper, we want to uncover how context affects the structure of utterances (vs lexical choice).</Paragraph>
    <Paragraph position="11"> Section 2 presents the different steps of our approach: context modeling (2.1), information structure analysis (2.2), applied discourse pragmatics (2.3) and NLG strategy (2.4). Section 3 illustrates these ideas through scenarios and we conclude (section 4) with a discussion of our work.</Paragraph>
  </Section>
class="xml-element"></Paper>