Some advances in transformation-based part of speech tagging
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Glr*: a robust grammar-focused parser for spontaneously spoken language
Glr*: a robust grammar-focused parser for spontaneously spoken language
Error-responsive feedback mechanisms for speech recognizers
Error-responsive feedback mechanisms for speech recognizers
A Semantic Based Approach for Spontaneous Spoken Dialogue Understanding
NLP '00 Proceedings of the Second International Conference on Natural Language Processing
DiaSumm: flexible summarization of spontaneous dialogues in unrestricted domains
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Understanding unsegmented user utterances in real-time spoken dialogue systems
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
FNDS: a dialogue-based system for accessing digested financial news
Journal of Systems and Software
Web information retrieval based on user operation on digital maps
GIS '06 Proceedings of the 14th annual ACM international symposium on Advances in geographic information systems
Less-conscious information retrieval techniques for location based services
Proceedings of the 2009 International Workshop on Location Based Social Networks
Incremental speech translation
Incremental speech translation
Chinese utterance segmentation in spoken language translation
CICLing'03 Proceedings of the 4th international conference on Computational linguistics and intelligent text processing
Hi-index | 0.00 |
In this paper, we present a chunk based partial parsing system for spontaneous, conversational speech in unrestricted domains. We show that the chunk parses produced by this parsing system can be usefully applied to the task of reranking Nbest lists from a speech recognizer, using a combination of chunk-based n-gram model scores and chunk coverage scores.The input for the system is Nbest lists generated from speech recognizer lattices. The hypotheses from the Nbest lists are tagged for part of speech, "cleaned up" by a preprocessing pipe, parsed by a part of speech based chunk parser, and rescored using a backpropagation neural net trained on the chunk based scores. Finally, the reranked Nbest lists are generated.The results of a system evaluation are promising in that a chunk accuracy of 87.4% is achieved and the best performance on a randomly selected test set is a decrease in world error rate of 0.3 percent (absolute), measured on the new first hypotheses in the reranked Nbest lists.