<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-0703">
  <Title>Spoken Language Parsing Using Phrase-Level Grammars and Trainable Classifiers</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 MT System Overview
</SectionTitle>
    <Paragraph position="0"> The analyzer we describe is used for English and German in several multilingual human-to-human speech-to-speech translation systems, including the NESPOLE! system (Lavie et al., 2002). The goal of NESPOLE! is to provide translation for common users within real-world e-commerce applications. The system currently provides translation in the travel and tourism domain between English, French, German and Italian.</Paragraph>
    <Paragraph position="1"> NESPOLE! employs an interlingua-based translation approach that uses four basic steps to perform translation. First, an automatic speech recognizer processes spoken input. The best-ranked hypothesis from speech recognition is then passed through the analyzer to produce interlingua. Target language text is then generated from the interlingua. Finally, the target language text is synthesized into speech.</Paragraph>
    <Paragraph position="2"> This interlingua-based translation approach allows for distributed development of the components for each language. The components for each language are assembled into a translation server that accepts speech, text, or interlingua as input and produces interlingua, text, and synthesized speech. In addition to the analyzer described here, the English translation server uses the JANUS Recognition Toolkit for speech recognition, the GenKit system (Tomita &amp; Nyberg, 1988) for generation, and the Festival system (Black et al., 1999) for synthesis.</Paragraph>
    <Paragraph position="3"> NESPOLE! uses a client-server architecture (Lavie et al., 2001) to enable users who are browsing the web pages of a service provider (e.g. a tourism bureau) to seamlessly connect to a human agent who speaks a different language.</Paragraph>
    <Paragraph position="4"> Using commercially available software such as Microsoft NetMeeting(TM), a user is connected to the NESPOLE! Mediator, which establishes connections with the agent and with translation servers for the appropriate languages. During a dialogue, the Mediator transmits spoken input from the users to the translation servers and synthesized translations from the servers to the users.</Paragraph>
  </Section>
class="xml-element"></Paper>