Introduction

I am a postdoctoral researcher at the NLP department of MBZUAI, Abu Dhabi, and advised by Dr. Monojit Choudhury. My current research focuses on the intersection of culture and LLMs, encompassing the cultural alignment of LLMs and gearing LLMs for diverse aspects of culture. I graduated with a PhD in Computer Science and Engineering from the University of Buffalo, New York, in Spring 2024. Focusing on argumentation mining from discourse and persuasive conversational systems, I was advised by Dr. Rohini K. Srihari. My broader research interests include purposeful conversational systems such as conversational systems for persuasion, deliberation, and negotiation and studying their cross-cultural use.

Top Publications

• Integrating Argumentation and Hate-Speech-based Techniques for Countering Misinformation. Sougata Saha and Rohini Srihari. EMNLP 2024. Dataset
• ArgU: A Controllable Factual Argument Generator. Sougata Saha and Rohini Srihari. ACL 2023. Code
• Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues. Sougata Saha and Rohini Srihari. ICON 2023.
• Turiya at dialam-2024: Inference anchoring theory based LLM parsers. Sougata Saha and Rohini Srihari. Proceedings of the 11th Workshop on Argument Mining @ ACL 2024.
• Turiya at perpectivearg2024: A multilingual argument retriever and reranker. Sougata Saha and Rohini Srihari. Proceedings of the 11th Workshop on Argument Mining @ ACL 2024.
• Rudolf Christoph Eucken at SemEval-2023 Task 4: An Ensemble Approach for Identifying Human Values from Arguments. Sougata Saha and Rohini Srihari. SemEval @ ACL 2023. Code
• Dialo-AP: A Dependency Parsing Based Argument Parser for Dialogues. Sougata Saha, Souvik Das and Rohini Srihari. COLING 2022. Code
• EDU-AP: Elementary Discourse Unit based Argument Parser. Sougata Saha, Souvik Das and Rohini Srihari. SIGDIAL 2022 (Best Paper Nomination https://2022.sigdial.org/best-paper-nominations/). Code
• Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection. Souvik Das, Sougata Saha and Rohini Srihari. COLING 2022.
• Proto-Gen: An end-to-end neural generator for persona and knowledge grounded response generation. Souvik Das, Sougata Saha and Rohini Srihari. Proceedings of the 1st Workshop on Customized Chat Grounding Persona and Knowledge @ COLING 2022.
• Stylistic Response Generation by Controlling Personality Traits and Intent. Sougata Saha, Souvik Das and Rohini Srihari. Proceedings of the 4th Workshop on NLP for Conversational AI @ ACL 2022. Code
• UB Health Miners@SMM4H’22: Exploring Pre-processing Techniques To Classify Tweets Using Transformer Based Pipelines. Roshan Khatri, Sougata Saha, Souvik Das, Rohini Srihari. Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task @ COLING 2022.
• Let’s Chat: Understanding User Expectations in Socialbot Interactions. Elizabeth Soper, Erin Pacquetet, Sougata Saha, Souvik Das, Rohini Srihari. Proceedings of the Second Workshop on Bridging Human–Computer Interaction and Natural Language Processing @ NAACL 2022.
• Proto: A Neural Cocktail for Generating Appealing Conversations. Sougata Saha, Souvik Das, Elizabeth Soper, Erin Pacquetet, Rohini Srihari Proceedings of the Alexa Prize SocialBot Grand Challenge 4, 2021.
• Similarity Based Label Smoothing For Dialogue Generation. Sougata Saha, Souvik Das, Rohini Srihari. ICON 2022.
• Autobots Ensemble: Identifying and Extracting Adverse Drug Reaction from Tweets using Transformer Based Pipelines. Sougata Saha, Souvik Das, Prashi Khurana, Rohini Srihari. Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task @ COLING 2020.
• Medical Literature Mining and Retrieval in a Conversational Setting. Souvik Das, Sougata Saha, Rohini Srihari. International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation, 2020.

Teaching

• Instructor for Introduction to Information Retrieval (CSE 4/535) - Fall 2022
  • Course Syllabus: CSE535-Syllabus-Fall2022.pdf
  • Class Pictures: cse_535_class_pics
• Teaching Assistant for Natural Language Processing and Text Mining (CSE 635) - Spring 2022
• Teaching Assistant for Introduction to Information Retrieval (CSE 4/535) - Fall 2021
• Teaching Assistant for Natural Language Processing and Text Mining (CSE 635) - Spring 2021
• Teaching Assistant for Introduction to Information Retrieval (CSE 4/535) - Fall 2020
• Teaching Assistant for Introduction to Machine Learning (CSE 4/575) - Fall 2020

Professional Activities

• Organizer, 9th Workshop on Argument Mining at Coling 2022
• Conference reviewer, (EMNLP 2022, COLING 2022, ICON 2022)
• Journal Reviewer, The journal of Artificial Intelligence, Elsevier
• President, UB Computer Science and Engineering Graduate Student Association (CSE GSA) 2020-2021
• Team Leader, Proto @ Alexa Prize Socialbot Grand Challenge 4, 2020-2021