Morphological based language models for inflectional languages
作者： Tomas Brychcin , Miloslav Konopik
DOI: 10.1109/IDAACS.2011.6072829
关键词:
摘要: This paper shows a method to improve the language modeling for inflectional languages such as Czech and Slovak language. Methods are based upon principle of class-based models, where word classes derived from morphological information. Our experiments show that linear interpolation with models outperforms stand-alone N-gram model about 10–30%.
sci-hub.se 参考文章(4)
Pavel Ircing, Aleš Pražák, Luděk Müller, Language Model Adaptation Using Different Class-Based Models SPECOM 2007 Proceedings. ,(2007)
Dimitra Vergyri, Andreas Stolcke, Kevin Duh, Katrin Kirchhoff, Morphology-Based Language Modeling for Arabic Speech Recognition conference of the international speech communication association. ,(2004)
A. P. Dempster, N. M. Laird, D. B. Rubin, Maximum Likelihood from Incomplete Data Via theEMAlgorithm Journal of the Royal Statistical Society: Series B (Methodological). ,vol. 39, pp. 1- 22 ,(1977) , 10.1111/J.2517-6161.1977.TB01600.X
Stanley F. Chen, Joshua Goodman, An empirical study of smoothing techniques for language modeling Computer Speech & Language. ,vol. 13, pp. 359- 394 ,(1999) , 10.1006/CSLA.1999.0128