Morphological based language models for inflectional languages
Tomáš Brychcín, Miloslav Konopík · 2011
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%.