<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2191">
  <Title>Spoken-Language Translation Method Using Examples</Title>
  <Section position="8" start_page="1075" end_page="1076" type="evalu">
    <SectionTitle>
5 Discussion
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="1075" end_page="1075" type="sub_section">
      <SectionTitle>
5.1 Integration of Speech and Language
</SectionTitle>
      <Paragraph position="0"> A mechanism for spontaneous speech translation must be consistent with a mechanism for handling associative knowledge, such as translation usage examples and word co-occurrence information for rnemory-b~ed processing, and with a mechanism for logical structure analysis according to detailed rules for each processing phase in the Transfer-Driven MT processing. Under the process, a study should be carried out on building a stochastic language model using both syntactic and semantic information for speech understanding.</Paragraph>
    </Section>
    <Section position="2" start_page="1075" end_page="1076" type="sub_section">
      <SectionTitle>
5.2 Related Research
</SectionTitle>
      <Paragraph position="0"> On the other hand, some studies hope to build spoken language translation systems using a certain interlingua method. A semantic parser is a typical example of this method. In particular, &amp;quot;semantic pattern based parsing&amp;quot; in JANUS, CMU's speech to speech translation system \[Woszczyna93, Levin95\] uses frame based semantics with a semantic phrase grammar and the operation of the parser is viewed as &amp;quot;phrase spotting.&amp;quot; Another one is MIT's multilingual  GALAXY: a human-language interface to on-line travel information \[Goddean94\]. The system makes use of 'semantic frame representation' so as to paraphrase a recognized speech input utterance into a concrete and simple expression that contbrms with one of the system's internal representations and makes the utterance meaning easy to handle. Itowever, in extracting the meaning of an inlmt sentence, many default values are required so as to execute heuristic inferences. The inference is too powerful in explaining a speaker's intention and the propositional content of the utterance by one key word or phrase. Such a method may work well in a certain domain, but less scalability may be revealed when making a larger prototype system.</Paragraph>
      <Paragraph position="1"> VERBMOBIL is a typical translation system for face-to:face dialogue \[Wahlster93\]. This system adopts English as a dialogue language for human-machine interface and makes use of DRT-based semantic representation units.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>