Semantic Role Labelling: A Systematic Review of Approaches, Challenges, and Trends for English and Indian Languages

Abstract

This systematic review looks at the advances, trends, and challenges within semantic role labelling (SRL) for both English and Indian languages. SRL stands as a pivotal undertaking in the realm of natural language processing (NLP), entailing the identification of semantic connections between predicates and their corresponding arguments in a given sentence. The synthesis of findings from publicly available NLP repositories in this review sheds light on the progression of SRL methodologies and their use across various linguistic contexts. The investigation examines the distinct hurdles presented by Indian languages, which are characterised by their morphological complexity and syntactic variability, juxtaposed with the more widely studied English language. Furthermore, we perform an analysis of the impact of sophisticated machine learning algorithms, particularly deep learning, on enhancing SRL efficacy across these languages. The review identifies key research gaps and proposes future research pathways to address the complex nature of SRL in multilingual environments. By offering a comprehensive overview of the evolutionary trajectory of SRL research, the primary objective of this article is to contribute to the advancement of more resilient and adaptable NLP systems capable of accommodating a myriad of languages.