tailieunhanh - Báo cáo khoa học: "Improving Translation through Contextual Information"

This paper proposes a two-layered model of dialogue structure for task-oriented dialogues that processes contextual information and disambiguates speech acts. The final goal is to improve translation quality in a speech-to-speech translation system. | Improving Translation through Contextual Information Maite Taboada Carnegie Mellon University 5000 Forbes Avenue Pittsburgh. PA 15213 taboada @ Abstract This paper proposes a two-layered model of dialogue structure for task-oriented dialogues that processes contextual information and disambiguates speech acts. The final goal is to improve translation quality in a speech-to-speech translation system. 1 Ambiguity in Speech Translation For any given utterance out of what we can loosely call context there is usually more than one possible interpretation. A speaker s utterance of an elliptical expression like the figure twelve fifteen might have a different meaning depending on the context of situation the way the conversation has evolved until that point and the previous speaker s utterance. Twelve fifteen could be the time a quarter after twelve the price one thousand two hundred and fifteen the room number one two one five and so on. Although English can conflate all those possible meanings into one expression the translation into other languages usually requires more specificity. If this is a problem for any human listener the problem grows considerably when it is a parser doing the disambiguation. In this paper I explain how we can use discourse knowledge in order to help a parser disambiguate among different possible parses for an input sentence with the final goal of improving the translation in an end-to-end speech translation system. The work described was conducted within the JANUS multi-lingual speech-to-speech translation system designed to. translate spontaneous dialogue in a limited domain Lavie et al. 1996 . The machine translation component of JANUS handles these problems using two different approaches the Generalized Left-to-Right parser GLR Lavie and Tomita 1993 and Phoenix the latter being the focus of this paper. The author gratefully acknowledges support from la Caixa Fellowship Program. ATR Interpreting Laboratories. and Project Enthusiast.