Named entity tagged language models

Author

Gotoh, Yoshihiko ; Renals, Steve ; Williams, Gethin

Author_Institution

Dept. of Comput. Sci., Sheffield Univ., UK

Volume

1

fYear

1999

fDate

15-19 Mar 1999

Firstpage

513

Abstract

We introduce named entity (NE) language modelling, a stochastic finite state machine approach to identifying both words and NE categories from a stream of spoken data. We provide an overview of our approach to NE tagged language model (LM) generation together with results of the application of such a LM to the task of out-of-vocabulary (OOV) word reduction in large vocabulary speech recognition. Using the Wall Street Journal and Broadcast News corpora, it is shown that the tagged LM was able to reduce the overall word error rate by 14%, detecting up to 70% of previously OOV words. We also describe an example of the direct tagging of spoken data with NE categories

Keywords

error statistics; finite state machines; natural languages; speech recognition; stochastic processes; Broadcast News corpus; Wall Street Journal corpus; large vocabulary speech recognition; named entity tagged language models; out-of-vocabulary word reduction; spoken data; stochastic finite state machine; word error rate reduction; Automata; Broadcasting; Computer science; Error analysis; Hidden Markov models; Natural languages; Speech recognition; Stochastic processes; Tagging; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on

Conference_Location

Phoenix, AZ

ISSN

1520-6149

Print_ISBN

0-7803-5041-3

Type

conf

DOI

10.1109/ICASSP.1999.758175

Filename

758175