A Vowel Based Word Splitter to Improve Performance of Existing Nepali Morphological Analyzers on Words Borrowed from Sanskrit

Authors

  • Madhusudan Adhikari Department of Computer Science and Engineering, School of Engineering, Kathmandu University
  • Aatish Neupane Department of Computer Science and Engineering, School of Engineering, Kathmandu University

DOI:

https://doi.org/10.3126/kuset.v14i1.63465

Keywords:

Natural Language Processing(NLP), Morphological analyzers, Sanskrit conjunction, Nepali morpho-analysis, Tatsama words

Abstract

Nepali lexicon is rich in words borrowed from Sanskrit language, called "Tatsama" words. These words have a specific set of rules to split them into affixes and morphemes. This paper details these rules and describes an implementation that can be used to improve existing Nepali Morphological Analyzers which do not yet implement concrete rules for these kinds of words.

Downloads

Download data is not yet available.
Abstract
40
PDF
43

Downloads

Published

2020-04-30

How to Cite

Adhikari, M., & Neupane, A. (2020). A Vowel Based Word Splitter to Improve Performance of Existing Nepali Morphological Analyzers on Words Borrowed from Sanskrit. Kathmandu University Journal of Science, Engineering and Technology, 14(1). https://doi.org/10.3126/kuset.v14i1.63465

Issue

Vol. 14 No. 1 (2020)

Section

Original Research Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use. If you remix, adapt, or build upon the material, you must license the modified material under identical terms.