[month] [year]

Arghya B – Breaking language barriers

Arghya Bhattacharya, supervised by Dr. Manish Srivastava received his Master of Science – Dual Degree in  Computational Linguistics (CL). Here’s a summary of his research work on Breaking language barriers: A study on advancing aspect-based sentiment analysis for low resource languages:

This thesis focuses on the challenges of sentiment analysis and its variants, such as Aspect Term Extraction and Aspect Term Polarity Classification, in low-resource languages like Hindi. We explore methods to extract language-invariant features for sentiment analysis tasks, highlighting the task-dependency of this approach. Additionally, we identified a gap in the state of the existing gold standard dataset for Hindi and proposed a methodology for developing a high-quality dataset for this task. To further improve performance, we develop a novel architecture that achieves new state-of-the-art results for Hindi and near-state-of-the-art results for English, and demonstrates the effectiveness of the method in a multilingual setting. Overall, the thesis highlights the importance of developing language-specific solutions for sentiment analysis tasks in low-resource languages.

July 2023