[month] [year]

Tanvi Kamble

Tanvi Kamble  supervised by Dr. Manish Shrivastava  received her Master of Science –  Dual Degree  in Computational Linguistics (LCD). Here’s a summary of her research work on Enhancing Event Causality Detection in English and Hindi Languages:

The widespread use of artificial intelligence has resulted in significant advancements in the field of Natural Language Processing, with text summarization and question answering models being some of the most sought-after applications. By understanding the Causal Relationships between Events within a text, we can gain valuable insights into how Events influence each other, leading to more accurate and sophisticated model outcomes. This thesis is an attempt towards improving Event Causality through various ways. The thesis commences with a comprehensive examination of Events and States, outlining their various classifications and the relationships between them. This foundational discussion establishes the context for the exploration of Event Causality. It then delves into existing research on Event Causality identification highlighting areas for potential contribution Recognizing the scarcity of datasets focused on Event Causality in the Hindi language, this thesis introduces the Hindi Causal TimeBank. This dataset is built upon the existing Hindi TimeBank containing about 1000 news articles and can serve as a crucial resource for developing and training Event Causality models for Hindi-language text. The thesis elaborates on the different types of Causal Relations annotated within the dataset. The primary focus of this thesis lies in the advancement of Event Causality identification. Specifically, it explores the use of graph-based models (Graph Attention Networks (GAT)). GATs are well-suited for representing complex relationships between entities and Events. This thesis presents a series of experiments designed to improve results on Event Causality identification, aiming to outperform the current state-of-the-art methods. The performance of these models is evaluated across a range of datasets, including the newly developed Hindi Causal TimeBank. This thesis makes a significant contribution to the field of Event Causality. Improved Event Causality understanding has implications for information retrieval, machine translation, and knowledge graph construction. The introduction of the Hindi Causal Time Bank further expands the scope of this research into a crucial and understudied language.

November 2024