Statistics-based segment pattern lexicon - A new direction for Chinese language modeling

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 1998, Pages 169-172

  Yang, Kae Cherng ^a   Ho, Tai Hsuan ^a   Chienq, Lee Feng ^b   Lee, Lin Shan ^a,b  

^a NATIONAL TAIWAN UNIVERSITY   (Taiwan)

^b ACADEMIA SINICA   (Taiwan)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS; SIGNAL PROCESSING;

CHINESE CHARACTERS; CHINESE LANGUAGE; CHINESE LANGUAGE MODELING; CHINESE SENTENCE; LANGUAGE MODEL; SEGMENT PATTERN; STATISTICAL APPROACH; TRAINING CORPUS;

NATURAL LANGUAGE PROCESSING SYSTEMS;

EID: 0031623659     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1998.674394     Document Type: Conference Paper

References (5)

1. R. Kneser, "Statistical Language Modeling Using a Variable Context Length", Proc. ICSLP, 1996, I, pp 494-497
2. S. Deligne, F. Bimbot, "Language Modeling by Variable Length Sequences: Theoretical Formulation and Evaluation of Multigrams", Proc. ICASSP, 1995, I, 169-172
3. Chinese Knowledge Information Group, Technical Report 93-02. Institute of Information Science, Academia Sinica, Taiwan.
4. H. Law, C. Chan, "Ergodic Multigram HMM Integrating Word Segmentation And Class Tagging For Chinese Language Modeling", Proc. ICASSP, 1996, I, 196-199
5. H. Ney, U. Essen, R. Kneser, "On Structuring Probabilistic Dependences Stochastic Language Modeling", Computer Speech and Language, 1994, vol.8, 1-38