Quantitative Analysis of Lexico Semantic Relationship of Adjectives in Saraiki Language: A Corpus-based Study

Abstract

This research paper focuses on the lexico-semantic relation of adjectives in the Saraiki language used in books. The study aims to investigate the kinds of lexico-semantic association of adjectives in Saraiki language. A Corpus of one million words of the Saraiki language is developed through the books “Bol Chaal” and “ Wisaakh” using the Apache open NLP library. Out of a one-million-word corpus, 1500 words of the Saraiki language are extracted to analyze. The frequency of lexico-semantic relations between adjectives is examined or analyzed by quantitative data analysis. 3A model presented by Wallis and Nelson(2001) is used to carry out this research and analyze the gathered data. The findings show that the frequency percentage of antonyms, synonyms, masculine and feminine, homophones, meronyms, and collocation in lexical relation with the adjectives in the Saraiki language is illustrated by drawing tables.