Sukannya Purkayastha M.Sc.

FB 20: Informatik

Ubiquitous Knowledge Processing (UKP) Lab


work +49 6151 16-28574

Work S4|22 304
Dolivostr. 15
64293 Darmstadt


  • Natural Language Processing that involves
    • Argument Mining
    • Argument and Counter Argument Generation
    • Multilinguality


Framing of Arguments in Public Discourse about Critical Infrastructures (Working Title)

With the advent of the internet, discussions about critical and controversial topics has mainly shifted to online forums and social media websites due to their huge popularity. The growing spread of misinformation and conspiracy theories pose a serious challenge to the society. Due to the emergence of deep learning, it is possible to devise a way to tackle these challenges by employing the existing imformation available in the large scale language models. In this PhD project, we aim to develop methods to retrieve and generate arguments that can debunk this misinformation and also counter arguments based on refuting facts and their underlying worldviews.

2018 – 2021 MS (Research), Indian Institute of Technology, Kharagpur, India
2013 – 2017 B.Tech (Computer Science), Gauhati University, Assam, India
05/2021 – 07/2022 Researcher, TCS Research and Innovation, Kolkata
Supervisors: Sushant Vale and Sreedhar Reddy.
Project: Knowledge Guided Conversation Generation
05/2020 – 08/2020 Research intern, IBM Research Labs, Bangalore, India
Supervisors: Saswati Dana and Dinesh Garg.
Project: Knowledge Graph Question Answering using SPARQL silhouette generation

Purkayastha Sukannya, Dana Saswati, Garg Dinesh, Khandelwal Dinesh and Bhargav GP Shrivatsa, ‘A Deep Neural Approach to KGQA via SPARQL Silhoeutte Generation’, IEEE International Joint Conference on Neural Networks (IJCNN), 2022

Purkayastha Sukannya, Mullick Ankan, Goyal Pawan and Ganguly Niloy, ‘A Framework to Generate High-quality Datapoints for Multiple Novel Intent Detection’, Findings of North American Association for Computational Linguistics (NAACL), 2022

Purkayastha Saugata and Purkayastha Sukannya, ‘A variant of Gradient descent Algo- rithm Based on Gradient Averaging’, 12th OPT Workshop on Optimization for Machine Learning at Neural Information Processing Systems (NeurIPS), 2020

Purkayastha Sukannya, Mondal Ishani, Sarkar Sudeshna, Goyal Pawan and Pillai Jitesh K, ‘Drug-Drug Interactions Prediction based on Drug Embedding and Graph Auto-Encoder’, 19th IEEE International Conference on Bioinformatics and Bioengineering (BIBE) 2019, Athens, Greece, October 28-30, 2019

Mondal Ishani, Purkayastha Sukannya, Sarkar Sudeshna, Goyal Pawan, Pillai Jitesh, Bhattacharyya Amitava and Gattu Mahanandeeshwar , ‘Medical Entity Linking using Triplet Network’, 2nd ClinicalNLP workshop at North American Chapter of the Association for Computational Linguistics (NAACL) 2019, Minneapolis, USA, June 2-7, 2019