Named entity tagged language models
作者： Y. Gotoh , S. Renals , G. Williams
DOI: 10.1109/ICASSP.1999.758175
关键词:
摘要: We introduce named entity (NE) language modelling, a stochastic finite state machine approach to identifying both words and NE categories from stream of spoken data. provide an overview our tagged model (LM) generation together with results the application such LM task out-of-vocabulary (OOV) word reduction in large vocabulary speech recognition. Using Wall Street Journal Broadcast News corpora, it is shown that was able reduce overall error rate by 14%, detecting up 70% previously OOV words. also describe example direct tagging data categories.
sci-hub.se 参考文章(5)
Francis Kubala, Richard Schwartz, Rebecca Stone, Ralph Weischedel, NAMED ENTITY EXTRACTION FROM SPEECH ,(1998)
A.J. Robinson, An application of recurrent nets to phone probability estimation IEEE Transactions on Neural Networks. ,vol. 5, pp. 298- 305 ,(1994) , 10.1109/72.279192
R. Gaizauskas, K. Humphreys, H. Cunningham, Y. Wilks, University of Sheffield Proceedings of the 6th conference on Message understanding - MUC6 '95. pp. 207- 220 ,(1995) , 10.3115/1072399.1072418
S. Renals, M. Hochberg, Efficient evaluation of the LVCSR search space using the NOWAY decoder international conference on acoustics speech and signal processing. ,vol. 1, pp. 149- 152 ,(1996) , 10.1109/ICASSP.1996.540312
Daniel M. Bikel, Scott Miller, Richard Schwartz, Ralph Weischedel, Nymble: a High-Performance Learning Name-finder conference on applied natural language processing. pp. 194- 201 ,(1997) , 10.3115/974557.974586