<?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="6" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
5 Examples and Evaluation
</SectionTitle>
    <Paragraph position="0"> hi this section, we examine some polite expressions aud compound NPs that are common in telel)holm inquiry dialogues.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
5.1 Polite expressions
</SectionTitle>
      <Paragraph position="0"> An examl)le of the process for detecting the appropri ate SEF given a polite expression, is shown through the following subdialogue, focusing on discourse entities. null  (ul) Q: TouT~oku-youshi-wo okutte-kudasai. (Please send me a registration from.) (u2) S: Go-juusyo-wo onegai-shi-masu.</Paragraph>
      <Paragraph position="2"> where agent Q is the questioner and S is tfie secretariat. null This example can be recognized in the sendsomthing domain plan (m Section 2). First ul is recognized and understood a.s an utterance which illtroduces the domain plan. Then, fi)r the next utter ance by S (u2), since the system does not hohl the statement that S knows where to send a form, e.g.</Paragraph>
      <Paragraph position="3"> the wdue of Q's address, an utterance requesting the value of the destination is tirst predicted, and contextual information about the 'destination' concept can be provided (Step 1).</Paragraph>
      <Paragraph position="4"> Next, due to the constraint in tile plan, Rule 1 is applied to the contextual information. 'fhen, the preferable set of SEFs is derived by the rule(Step 2). Although the tirst Step 3 fails because &amp;quot;go-juusyo&amp;quot; is not the exact polite form of the first seed &amp;quot;okurisakf'(destination), the second time it, picks &amp;quot;yo-juusyo&amp;quot; ms the appropriate SEF because one of tim lower concepts, 'address', can be the next seed.</Paragraph>
      <Paragraph position="5"> On the other band, when processing 113, the set of polite tbrms for the 'address' is not preferred.</Paragraph>
      <Paragraph position="6">  normal 5 The communicative act type in the first column:is ~-e type of the utterance &amp;quot;to send&amp;quot;. The speaker in the sec ond colulnn is the speaker of the target SEF, with SP indicating the speaker in the first COblntn, and HR, hearer. Evaluati(m: We evaluated this tnethod by inspectlug SEFs for 'destinatiou' in the ATR diak)gue database\[4\]. The target corpus, whose topic is &amp;quot;Con fi~rence registration&amp;quot;, has 85 conversations, 195fi utterance units, and 3085 sentences. Moreover, the tar. get expressions are restricted to those uttered in a segment of the send-somet.hing domain plan. The evaluaLion was done in the tollowing way: 1. H.etrieve sentences which have the verb &amp;quot;okumg' (to Selld) or syllonylllOllS w~.rbs as tile lllaill verb of the sentelice (lfll sentences).</Paragraph>
      <Paragraph position="7"> Then, output the utterance refit together with the next utterance unit ( 161 pairs).</Paragraph>
      <Paragraph position="8">  2. Pick tim i)airs in which there is a expression about 'destination' (43 pairs).</Paragraph>
      <Paragraph position="9"> Filter by the send-something domain plan, and those pairs that are not recognized are elimi-.</Paragraph>
      <Paragraph position="10"> nated (32 pairs remain).</Paragraph>
      <Paragraph position="11"> 3. Cl~kssify the target expressions (68 expressions)  into tile othm&amp;quot;s territory (a2 polite and 12 norreal) and the spe.aker's (24 normal).</Paragraph>
      <Paragraph position="12"> The results are shown in the Tal)le 1. Tiffs inspec tion shows that ill (an&amp;quot; target, dOiqlaill, I~lle framework described m the paper is useful for selecting a surface expression that is appropriate in the dialogue situation.</Paragraph>
      <Paragraph position="13"> Example (Vocative): Consider the subdialogue that follows tile above subdialogue:</Paragraph>
      <Paragraph position="15"> After recognizing 114 by the saule interaction plan a.s the first example, a variable node corresponding to Q's name is instantiated and bound to &amp;quot;Suzuki Mayumi&amp;quot;. Then, for the next utterance by S (u5), we can predict the confirmation utterance including the contextual intbrmation about Q's name as a discourse entity. Consequently, we can select the SI';F &amp;quot;Suzuki-Mayumi-sama&amp;quot;(polite form) by the contextual information and the applicable rule 2.</Paragraph>
      <Paragraph position="16"> ACII~S DE COLING-92, NAM'Es, 23-28 hotrr 1992 1 1 5 5 Pace, OF COLING-92, NANTES, AUG. 23-28, 1992</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
5.2 Compomld NPs
</SectionTitle>
      <Paragraph position="0"> Compound NPs can roughly be classified into l)rol)er NPs and common NPs. Predicting SEFs from a common NP is usually done by shifting the seed to the upper level (by Rule 3). For example;  In this example, u6 instantiates the send something domain plan by tile effect chain\[7\]. Then, since we know from u7 that the effect (the goal of this subdialogue) is not satisfied, we can predict that the next utterance hy Q (u8) ruay concern introducing the action to send a form, and it. irmludes con textual information about 'application form'. In the knowledge base, 'form' is tile concept node just above 'application form'. Consequently, by applicable ruin 3, we select &amp;quot; YoushF(forn 0 directly.</Paragraph>
      <Paragraph position="1"> On the other l~and, predicting SEFs tbr proper NPs requires another rule to creat.e the donlain-dependent knowledge base for shortening, llerc, we use the dependency relationships within NP\[91 to abbreviate a proper compound NP. For exalnph~, applying this rule to a proper compound NP &amp;quot;Kyoto-Kokusai-Kaigijoff'(Kyoto International Conference Center), we get a preferable set of SEFs inelnding &amp;quot;Kyoio-</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Kaigijon&amp;quot;(Kyoto Conference Center) and &amp;quot;Kokusai-
Katgoou&amp;quot;(International Conference Center), ill addi-
</SectionTitle>
      <Paragraph position="0"> tion to the basic upper SEF &amp;quot;l(aiyzjou&amp;quot;(confcrence center). Consequently, we call select &amp;quot;KokusaikaigOou&amp;quot; in ul0 in the following subdialogue with  At the moment, we define a short link to con noel lexieal nodes created by abbreviation rules to the proper compound NP thai instantiates a variable node.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>