Title :
Morphological based language models for inflectional languages
Author :
Tomáš Brychcín;Miloslav Konopík
Author_Institution :
Department of Computer Science and Engineering, University of West Bohemia in Pilsen, Univerzitní
Abstract :
This paper shows a method to improve the language modeling for inflectional languages such as the Czech and Slovak language. Methods are based upon the principle of class-based language models, where word classes are derived from morphological information. Our experiments show that the linear interpolation with the class-based language models outperforms the stand-alone word N-gram language model about 10-30%.
Keywords :
"Interpolation","Computational modeling","Accuracy","Estimation","Vocabulary","Adaptation models","Educational institutions"
Conference_Titel :
Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), 2011 IEEE 6th International Conference on
Print_ISBN :
978-1-4577-1426-9
DOI :
10.1109/IDAACS.2011.6072829