Sciweavers

MT
2002

MARS: A Statistical Semantic Parsing and Generation-Based Multilingual Automatic tRanslation System

13 years 12 months ago
MARS: A Statistical Semantic Parsing and Generation-Based Multilingual Automatic tRanslation System
We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language translation between English and Mandarin Chinese for limited domains, such as air travel reservations. In MARS, machine translation is embedded within a complex speech processing task, and the translation performance is highly effected by the performance of other components, such as the recognizer and semantic parser, etc. All components in the proposed system are statistically trained using an appropriate training corpus. The speech signal is first recognized by an automatic speech recognizer (ASR). Next, the ASR-transcribed text is analyzed by a semantic parser, which uses a statistical decision-tree model that does not require hand-crafted grammars or rules. Furthermore, the parser provides semantic information that helps further re-scoring of the speech recognition hypotheses. The semantic content extracted by...
Yuqing Gao, Bowen Zhou, Zijian Diao, Jeffrey S. So
Added 22 Dec 2010
Updated 22 Dec 2010
Type Journal
Year 2002
Where MT
Authors Yuqing Gao, Bowen Zhou, Zijian Diao, Jeffrey S. Sorensen, Michael Picheny
Comments (0)