A Robust and E cientThree - Layered Dialogue
نویسندگان
چکیده
Das diesem Bericht zugrundeliegende Forschungsvorhaben wurde mit Mitteln des Bundesministers f ur Forschung und Technologie unter dem FF orderkenn-zeichen 01 IV 101 K/1 geff ordert. Die Verantwortung f ur den Inhalt dieser Arbeit liegt bei den Autoren. Abstract We present the dialogue component of the speech-to-speech translation system verbmobil. In contrast to conventional dialogue systems it mediates the dialogue while processing maximally 50% of the dialogue in depth. Special requirements (robustness and eeciency) lead to a 3-layered hybrid architecture for the dialogue module, using statistics , an automaton and a planner. A dialogue memory is constructed incrementally.
منابع مشابه
A Robust and E cient Three - Layered Dialogue Component fora Speech - to - Speech Translation System
We present the dialogue component of the speech-to-speech translation system verb-mobil. In contrast to conventional dialogue systems it mediates the dialogue while processing maximally 50% of the dialogue in depth. Special requirements (ro-bustness and eeciency) lead to a 3-layered hybrid architecture for the dialogue module , using statistics, an automaton and a planner. A dialogue memory is ...
متن کاملWord concept model: a knowledge representation for dialogue agents
Information extraction is a key component in dialogue systems. Knowledge about the world as well as knowledge specific to each word should be used for robust semantic processing. An intelligent agent is necessary for a dialogue system when meanings are strictly defined by using a world state model. A layered concept structure is proposed to represent knowledge associated with each word in a "sp...
متن کاملA Robust and Efficient Three-Layered Dialogue Component for a Speech-to-Speech Translation System
Das diesem Bericht zugrundeliegende Forschungsvorhaben wurde mit Mitteln des Bundesministers f ur Forschung und Technologie unter dem FF orderkenn-zeichen 01 IV 101 K/1 geff ordert. Die Verantwortung f ur den Inhalt dieser Arbeit liegt bei den Autoren. Abstract We present the dialogue component of the speech-to-speech translation system verbmobil. In contrast to conventional dialogue systems it...
متن کاملIncremental Dialogue Act Recognition: Token- vs Chunk-Based Classification
This paper presents a machine learning based approach to incremental dialogue act classification with a focus on the recognition of communicative functions associated with dialogue segments in a multidimensional space, as defined in the ISO 24617-2 dialogue act annotation standard. The main goal is to establish the nature of an increment whose processing will result in a reliable overall system...
متن کاملBehaviors and Layers in Spoken Dialogue Systems
The classical view of artificial intelligence (AI) is tied down by a number of problems. These problems indicate that it might be fruitful to approach AI applications, including spoken dialogue systems, in an alternative way. This paper overviews current attempts to apply the idea of layered behavior-based architectures in dialogue system development. It is concluded that there are both theoret...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1995