PART-OF-SPEECH N-GRAM AND WORD N-GRAM FUSED LANGUAGE MODEL

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 1803-1806

  Yamamoto, Hirofumi ^a   Sagisaka, Yoshinori ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Class N gram; MAP Estimation; Word clustering

Indexed keywords

COMPUTATIONAL LINGUISTICS;

CLASS N-GRAM; DATA SPARSENESS; LANGUAGE MODEL; MAP ESTIMATION; N-GRAMS; PART OF SPEECH; S-STATISTIC; TASK DEPENDENCIES; WORD CLUSTERING; WORD N-GRAMS;

SPEECH COMMUNICATION;

EID: 0011404834     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. F.Jelinek andR.L.M ercer:"Interpolated Estim ation of M arkov Source Param eters from Sparse Data," Pattern Recognition in Practice,pp. 381-397. NorthHolland, 1980
2. H.M asataki,Y.Sagisaka,K.Hisakiand T. Kawahara:"Task Adaptation Using M AP Estim ation in N-gram Language M odeling," Proc ICASSP,vol. 1,pp.783-786, 1997
3. Shuanghu Bai, Haizhou Li, Zhiwei Lin and Baosheng Yuan:”Building Class-based Language M odels with Contextual Statistics,” Proc ICASSP, vol. 1, pp.173-176, 1998
4. H.Yam am oto and Y.Sagisaka:"M ulti-Class Com posite N-gram Language M odel Based on Connection Direction, " Proc ICASSP,vol. 1, pp.533-536, 1999
5. C.Sam uelsson and W.Reichl:"A Class-Based Language M odel for Large-Vocabulary Speech Recognition Extracted from Part-of-Speech Sta-ti stics," ProcICASSP,vol. 1,pp.537-540, 1999