Open AccessEfficient Estimation of Nepali Word Representations in Vector Space
Author(s) -
Janardan Bhatta,
Dipesh Shrestha,
Santosh Nepal,
Saurav Pandey,
S Koirala
Publication year - 2020
Publication title -
journal of innovations in engineering education
Language(s) - English
Resource type - Journals
eISSN - 2773-823X
pISSN - 2594-343X
DOI - 10.3126/jiee.v3i1.34327
Subject(s) - nepali , word (group theory) , representation (politics) , computer science , artificial intelligence , natural language processing , space (punctuation) , vector space model , mathematics , linguistics , philosophy , geometry , politics , political science , law , operating system
Word representation is a means of representing a word as mathematical entities that can be read, reasoned and manipulated by computational models. The representation is required for input to any new modern data models and in many cases, the accuracy of a model depends on it. In this paper, we analyze various methods of calculating vector space for Nepali words and postulate a word to vector model based on the Skip-gram model with NCE loss capturing syntactic and semantic word relationships.
This is an attempt to implement a paper by Mikolov on Nepali words.