Computational Linguistics
A robust system for natural spoken dialogue
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
"Dialog Navigator": a question answering system based on large text knowledge base
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Efficient dialogue strategy to find users' intended items from information query results
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Open-domain voice-activated question answering
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Spoken interactive ODQA system: SPIQA
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 2
The LIMSI ARISE system for train travel information
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Confidence measures for dialogue management in the CU Communicator system
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Hi-index | 0.00 |
Adequate confirmation for keywords is indispensable in spoken dialogue systems to eliminate misunderstandings caused by speech recognition errors. Spoken language also inherently includes out-of-domain phrases and redundant expressions such as disfluency, which do not contribute to task achievement. It is necessary to appropriately make confirmation for important portions. However, a set of keywords necessary to achieve the tasks cannot be predefined in retrieval for a largescale knowledge base unlike conventional database query tasks. In this paper, we describe two statistical measures for identifying portions to be confirmed. A relevance score represents the matching degree with the target knowledge base. A significance score detects portions that consequently affect the retrieval results. These measures are defined based on information that is automatically derived from the target knowledge base. An experimental evaluation shows that our method improved the success rate of retrieval by generating confirmation more efficiently than using a conventional confidence measure.