File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/96/c96-1075_intro.xml
Size: 2,077 bytes
Last Modified: 2025-10-06 14:06:00
<?xml version="1.0" standalone="yes"?> <Paper uid="C96-1075"> <Title>Multi-lingual Translation of Spontaneously Spoken Language in a Limited Domain</Title> <Section position="2" start_page="0" end_page="0" type="intro"> <SectionTitle> 1 Introduction </SectionTitle> <Paragraph position="0"> JANUS is a multi-lingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In this paper we describe the current design and performance of the machine translation module of our system. The analysis of spontaneous speech requires dealing with problenls such as speech disfluencies, looser notions of grammaticality and the lack of clearly marked sentence boundaries. These problems are further exacerbated by errors of the speech recognizer. We describe how our machine translation system is designed to effectively handle these and other problems, hi an attempt to achieve both robustness and translation accuracy we use two different translation components: the (JLlt. module, designed to be more accurate, and the Phoenix module, designed to be more robust. Both modules follow an interlingua-based approach. The translation modules are designed to be language-independent in the sense that they each consist of a general processor that applies independently specified knowledge about different languages. This facilitates the easy adaptation of the system to new languages and domains. We analyze the strengths and weaknesses of each of the translation approaches and describe our work on combining them. Our current system is designed to translate spontaneous dialogues in the Scheduling domain, with English, Spanish and German as both source and target languages. A recent focus has been on developing a detailed end-to-end evaluation procedure to measure the performance and effectiveness of the system. We describe this procedure in the latter part of the paper, and present our most recent Spanish-to-English performance evaluation results.</Paragraph> </Section> class="xml-element"></Paper>