A Corpus-Based Analysis of The Lexico-Semantic Relationships of Verbs Used in Saraiki language Newspaper

Abstract

The present study intends to develop lexico-semantic relationships among Saraiki verbs. For this purpose, the semantic relationships of the English WordNet model established by Miller (1990) at Princeton University is considered as framework of the study. This study aims at promoting the Saraiki language and is a step towards establishing Saraiki WordNet in the upcoming years. A corpus of 1 million words were created from the Saraiki newspaper Jhoke and after text annotation and encoding, a list of 160 verbs were generated. The lexico-semantic relationships of verbs were developed with the help of machine-readable dictionary and the frequency of each relationship was found using Laurence Anthony’s Antconc 3.5.7 version. Results exhibited four semantic relations such as synonymy, antonymy entailment, and troponymywith a different frequency and percentage, essential for developing a WordNet. The lexico-semantic relationships of Saraiki can be helpful in developing digital applications and promotingSaraiki language