<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-3012">
  <Title>Language Generation</Title>
  <Section position="3" start_page="0" end_page="67" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A speaker's utterance may convey different meaning to a hearer. Such ambiguities can be resolved by emphasizing accents in different positions. Focus information is needed to select correct positions for accent information. To determine focus information, a speaker's intentions must be revealed. We apply speech act theory to written sentences, our input, to determine a speaker's intention. Subsequently our system will produce a speaker utterance, the result of analysis.</Paragraph>
    <Paragraph position="1"> Several research publications, such as (Steedman and Prevost, 1994) and (Klein, 2000), explore prosodic analysis for spoken language generation (SLG). Klein (2000) designs constraints for prosodic structures in the HPSG framework.</Paragraph>
    <Paragraph position="2"> His approach is based on an isomorphism of syntactic and prosodic trees. This approach is heavily syntax-driven and involves making prosodic trees by manipulation of the syntactic trees. This approach results in increased complexity since the type hierarchy of phrases must crossclassify prosodic phrases under syntactic phrases. Haji-Abdolhosseini (2003) extended Klein's approach. Rather than referring to syntax, Haji-Abdolhosseini sets the information domain to interact between the syntactic-semantic domain and the prosodic domain. His work reduces the complexity of type hierarchies and constraints which are not related to the syntactic structure. He designs the information structure and defines constraints for the HPSG framework. However his work limits the number of tone selections because he only defines two tone marks: rise-fall-rise and fall to annotate a sentence.</Paragraph>
    <Paragraph position="3"> Our work is inspired by Haji-Abdolhosseini's work. We design the focus structure for spoken language generation. Based on the focus theory (Von Heusinger, 1999), the focus part identifies what part of the sentence can be marked with the strong accent or emphasized by a high tone.</Paragraph>
    <Paragraph position="4"> By analyzing speech acts, we can understand how speech with prosody can convey distinct speaker intentions to a hearer. In the next section, we present an overview of our FET (Focus to Emphasize Tone) system and its processes. We will explain how to analyze focus information, design the FET structure, and find the relationships of focus with speech acts to prosodic marks in section 3.</Paragraph>
    <Paragraph position="5"> We implement our FET grammar for the Linguistic Knowledge Base (LKB) system (Copestake, 2002), generate a set of focus words, explain the FET environment, and show an example in section 4. In the last section, we conclude the current state of our work and the future work.</Paragraph>
  </Section>
class="xml-element"></Paper>