DEBJIT PAUL

Debjit Paul

Contact

+49 6221 54-3169
Email (click to copy)
Institut für Computerlinguistik
Im Neuenheimer Feld 325
D-69120 Heidelberg
Germany

About me:

Since May 2018, I am a Doctoral Student under the supervision of Prof. Dr. Anette Frank at the Department of Computational Linguistics at Heidelberg University and also a part of Research Training Group AIPHES.

My research interest lies in the area of natural language processing (NLP) where I have worked on building NLP models that can utilize external commonsense knowledge to perform different natural language understanding (NLU) tasks. I am particularly interested in problems that require models to exhibit social and emotional intelligence. One theme which is common throughout my research is the need to explicitly reason about a social situation. My primary research interest areas are :

  • Commonsense Reasoning
  • Interpretability and Explanable Machine Learning
  • Knowledge Based Reasoning

Prior to this, I have completed my Masters in Computer Science from Saarland University, Saarbrücken, Germany. I worked on handling noisy labels while training Neural Networks.

NEWS

Internship at Amazon Science (Alexa AI) working on Continual Learning. Oct 2021 - Feb 2022.
Our paper Generating Hypothetical Events for Abductive Inference is accepted in *Sem, August 2021.
Giving an invited talk on Commonsense Reasoning at Edinburgh Napier University, November 2020.
Our paper Social Commonsense Reasoning with Multi-Head Knowledge Attention is accepted in Findings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2020.
Attending Association for Computational Linguistics (ACL), July 2020.
Attending EurNLP 2019 in London, UK. October 2019.

CURRICULUM VITAE

Read my CV here.

Personal Webpage: DP

PUBLICATIONS

2021
+ -

CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts

Becker, M., Korfhage, K., Paul, D., Frank, A. (2021)

Proceedings of the 14th International Workshop on Computational Semantics (IWCS), Groningen, The Netherlands (Online).

COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion

Paul, D., Frank, A. (2021)

Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) , Online.

Generating Hypothetical Events for Abductive Inference

Paul, D., Frank, A. (2021)

Proceedings of The Tenth Joint Conference on Lexical and Computational Semantics (*SEM 2021), Online.
2020
+ -

Explaining Arguments with Background Knowledge -- Towards Knowledge-based Argumentation Analysis

Becker, M., Hulpus, I., Paul, D., Opitz, J., Kobbe, J., Stuckenschmidt, H., Frank, A. (2020)

Datenbank Spektrum (Special Issue: Argumentation Intelligence).

Argumentative Relation Classification with Background Knowledge.

Paul, D., Opitz, J., Becker, M., Kobbe, J., Hirst, G., Frank, A. (2020)

Proceedings of the 8th International Conference on Computational Models of Argument (COMMA 2020).

Social Commonsense Reasoning with Multi-Head Knowledge Attention

Paul, D., Frank, A. (2020)

In Findings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
2018
+ -