<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0712">
  <Title>Automatic Interpretation System Integrating Free-style Sentence Translation and Parallel Text Based Translation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A speech-to-speech translation system must integrate at least three components -- speech recognition, machine translation, and speech synthesis. In practice, each component does not always output the correct result for various inputs, and an error in one component often leads to an incorrect result being produced by the total system even for a limited domain. Clearly, we need ways to complement speech-to-speech translation systems that cannot reliably produce a correct result.</Paragraph>
    <Paragraph position="1"> Although some robust methods that make the erroneous results of other components acceptable have been proposed (Yumi et al., 1997; Furuse et al., 1998), there is no guarantee that the final output from a system will be appropriate even with these methods. To deal with this problem, we have taken a more practical approach to developing an automatic interpretation system where the user can obtain a correct result instead of having to apply additional operations and judgment.</Paragraph>
    <Paragraph position="2"> In actual use of a speech-to-speech translation system, an error in the speech-recognition or speechsynthesis components is not a large problem if the system has a screen that displays each result. The user of the system can correct errors in the recognition result on the screen, and can communicate by showing the other person the translated sentence on the screen.</Paragraph>
    <Paragraph position="3"> On the other hand, an error in the machine-translation component is critical because a user who is not familiar with the target language is unlikely to notice the error in some cases. When a nonsensical sentence is generated by machine translation, the user may realize that the listener does not understand the translated sentence. However, when a plausible sentence that means something different from the intended meaning is generated by the machine translation, the user may incorrectly assume that the utterance was properly communicated. Consequently, the user can seldom be sure that the listener correctly understood the intended meaning when using a speech-to-speech translation system. A conversa-Association for Computational Linguistics.</Paragraph>
    <Paragraph position="4"> Algorithms and Systems, Philadelphia, July 2002, pp. 85-92. Proceedings of the Workshop on Speech-to-Speech Translation: tion could continue for some time before it became apparent that the two sides misunderstood what the other was saying.</Paragraph>
    <Paragraph position="5"> Moreover, if the user realizes that there is an error in the machine translation, correcting it will be difficult. Without knowing the source of the error, the user cannot modify the input to obtain a correct result.</Paragraph>
    <Paragraph position="6"> These error problems severely limit the usability of speech-to-speech translation.</Paragraph>
    <Paragraph position="7"> In this paper, we propose an automatic interpretation system that integrates free-style sentence translation and parallel text based translation. In this system, free-style sentence translation accepts natural language sentences and translates them by machine translation without guaranteeing the quality of the translation. On the other hand, parallel text based translation uses parallel bilingual sentences registered in the system and translates a registered sentence by referring to the corresponding translation. Although this translation process limits the input to registered sentences, it is a robust means of handling input with recognition errors and consistently provides a correct translation. We integrated these two types of translation to realize a robust translation system where the two types of translation compensate for the shortcomings of each other.</Paragraph>
    <Paragraph position="8"> For appropriate integration of free-style sentence translation and parallel text based translation, we had to consider three main points.</Paragraph>
    <Paragraph position="9">  1. User interface: how best to present the two functions to the user? 2. Content of registered sentences: How many utterances should be covered by registered sentences? null 3. Retrieval system: What methods of searching among the registered sentences should be pro- null vided to the user? In this paper, we discuss these three points with respect to a translation system for Japanese travelers in the overseas travel domain. We construct a model of the integration of free-style sentence translation and parallel text based translation in Section 2. We describe a prototype system based on the model in Section 3 and evaluate it in Section 4. Related work on translation systems utilizing parallel text are discussed in Section 5, and we conclude in Section 6.</Paragraph>
  </Section>
class="xml-element"></Paper>