Development of Punjabi Noun Synsets and Lexico-Semantic relations.

Abstract

This study aims developing synsets of noun of Punjabi Language (PL) in Shahmukhi. This is a corpus-based study. The study has developed a corpus of 2 million words of Punjabi Language in Shahmukhi script for selecting nouns to develop their synsets. The corpus of Punjabi Language was POS tagged and processed through software: AntConc.3.4.4.0 for getting nouns. The list of 1000 nouns was retrieved in English with respect to semantic categories. The developed list of nouns has been further translated from English to Gurmukhi to Shahmukhi using software: Akhar 2016. For the purpose of assistance, Princeton WordNet and Punjabi dictionaries were used in the construction of Punjabi noun synsets. As a result, 5000 synsets of nouns have been developed in term of identity number, word, grammatical category, synsets of noun, number of senses and sentence examples.