<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-4182">
  <Title>PRI~;DICTING NOUN~PIIRASE SURFACh; I~'ORMS USING Q~ONTEXTUAL \[NFORMA'PION</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A high-quality spoken-language processing system must use knowledge of dialogue and spoken-language.</Paragraph>
    <Paragraph position="1"> Using dialogue knowledge facilitates understanding and predicting utterances in context. Using spoken-language knowledge, that is knowledge about how tile speaker expresses what he/she wants to say, makes it possible for the system to recognize and generate the more complex expressions that are nornmlly ased ill our daily dialogues.</Paragraph>
    <Paragraph position="2"> To make language processing in the whole spokenlangnage processing system more efficient, it. is vital how to select the correct speech recognition output in the speech-language interface. The use of discourse-level knowledge is an effective way to do this\[6\]\[11\]. For example, MINDS\[6\] applied dialogue-level knowledge, particularly for propositional contents, to predict the expected utterance form for the speech recognition, ilowever, although MINDS showed good resuits, several llroblems remain before it can lie made into a complete spoken-language processing system:  1. how to construct the dialogue structure for the given domain, 2. how to treat predictive concepts regarding not only the propositional contents but also the speaker's intention, 3. and, how to etmose a set of surface forms tbat  the speaker might utter about the predicted concept. null Also, MINDS was concerned with a system to participate in human-machine dialogue. On the other band, we want to monitor a human-human dialogue.</Paragraph>
    <Paragraph position="3"> We proposed a dialogue understanding model\[7\], and a context-sensitive method to predict abstract information allout both tile intentional and propositional contents of tile next utterance\[11\]. These are our answers to the above problems 1 and 2.</Paragraph>
    <Paragraph position="4"> From tile point of view of human behavior, a potential approacb to selecting the appropriate surface erpression forms (SEFs) is using spoken-lauguage knowledge. In general, when we are talking about a concept X, there are many possible surface expressious and forms to represent X. From a psychological (or psyeholinguistic) point of view, Clark\[3\] pointed out five abstract factors which should be considered ill ,asking what linguistic devices should speakers use ?. These are: knowledge of the listener, the coopevalive principle, the reality principle, the social context, and the linguistic devices available. In the eomputatioual linguistics area, Appelt\[1\] has developed a framework to generate a sentence in a context-sensitive way, based on speech act tbeories. Unfortunately, however, there also remains, as he described ms a future study, the problem of choosing a lexically appropriate SEF from among candidates in a social conlexl.</Paragraph>
    <Paragraph position="5"> This paper describes a context-sensitive framework for selectiug all SEF for noun-phrases(NPs). This method is sensitive to botb tbe utterance situation and the history of the dialogue. To do this, first, we analyze the relations between concepts and SEFs, and between applicable situations and contexts, using a corpus of Japanese inquiry dialogues. Then, we make a domain-dependent knowledge source for NP usage, and define rules driven by applicable conditions to determine a set of possible SEFs in the knowledge base. Finally, we give exanaples of the SEI&amp;quot; selection, especially for polite expressions, deictifi expressions, and compound NPs, which are common in our target domain, and describe a simple experiment to evaluate using the ATR dialogue database. The result show tllat tile method can choose tbe contextually correct expression from the speech recognition output candidates, and can be used in tile generation module of a spoken-language processing system to generate and determine all appropriate expression under tile dialogue situation.</Paragraph>
    <Paragraph position="6"> Throughout this paper, all examples are in Japanese and written in italic. English translations follow in parentheses. NP denotes a noun phrase, and SEF denotes a surface expression form. SEFs are enclosed ill double quotation marks and concepts are enclosed in single quotation marks.</Paragraph>
  </Section>
class="xml-element"></Paper>