STHREE: Stemmer for Malayalam using three pass algorithm

K. Pragisha, P. C. Reghuraj · 2013

This paper reports the design of a three pass stemmer STHREE for Malayalam. The language is rich in morphological variations but poor in linguistic computational resources. The system returns the meaningful root word of the input word in 97% of the cases when tested with 1040 words. This is a significant improvement over the reported accuracy of SILPA system, the only known stemmer for Malayalam, with the same test data sets.

Read the paper · More papers on PaperTik