Combining lexical and morphological knowledge in language model for inflectional (Czech) language

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 705-708

  Nouza, Jan ^a   Drabkova, Jindra ^a  

^a TECHNICAL UNIVERSITY OF LIBEREC   (Czech Republic)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL LINGUISTICS; SPEECH RECOGNITION;

BIGRAMS; CLASS STATISTICS; CLASS-BASED LANGUAGE MODEL; LANGUAGE MODEL; SMOOTHING TECHNIQUES; SPARSE DATA;

MODELING LANGUAGES;

EID: 85009247777     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Hajic J.,: Disambiguation of Rich Inflection - Computational Morphology of Czech. Charles University Press - Karolinum, Prague. In print.
2. Byrne W., Hajic J., Ircing P., Krbec P., Psutka J.: Morpheme Based Language Models for Speech Recognition of Czech. In Proc. of TSD2000 Workshop, Brno, Sept. 2000, pp. 211-216.
3. Nouza, J.: Strategies for Developing a Real-Time Continuous Speech Recognition System for Czech Language. In Proc. of TSD2002 Workshop, Brno, Sept. 2002.
4. Witten, I. H. and Bell, T. C.: The Zero-Frequency Problem: Estimating the Probabilities of Novel Events in Adaptive Text Compression. IEEE Transactions on Information Theory, 37(4), (1991) pp. 1085-1094.
5. Kneser R., Ney H.: Improved Backing-off for N-gram Language Modeling. In Proc. of ICASSP'1995, Detroit, pp. 181-184.
6. Hajic J., Hladka B.: Probabilistic and Rule-Based Tagger of an Inflective Language - a Comparison. In Proc. of the 5th Conference on Applied Natural Language Processing, Washington, 1997, pp. 111-118
7. http://ckl.mff.cuni.cz/ufal/