View the Project on GitHub

Tuhin Chakrabarty


About me

I am a PhD student in Computer Science at Columbia University. Within the department I am a part of the Natural Language Processing group, where I am advised by Professor Smaranda Muresan . I also work with Professor Violet Peng and Professor Kathleen McKeown. My research interests are broadly in Natural Language Processing and Machine Learning, with special focus in Creative language generation (both at sentence level and Long Form), Role Of Structured Common sense in Downstream Tasks & Discourse and Argumentation. Prior to joining Grad school I was an engineer at UBER and Amazon.

Research Focus

While I enjoy working on most topics in Natural Language Processing, few of my research interests and directions are:

Here is my Google Scholar Page


3 Long Papers under submission at EMNLP

I helped building a demo for interactive story generation [Link Here] where given a title a model generates a five sentence short story :) Play with it.

Joining IBM AI Research as a summer 2020 intern where I will be supervised by Avirup Sil working on Question Answering



1) R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge
In Proceedings of ACL 2020 ,Seattle, WA.
Tuhin Chakrabarty , Debanjan Ghosh, Smaranda Muresan and Nanyun Peng
[pdf] [Code and Data] [Slides]

2) DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking
In Proceedings of the ACL 2020 ,Seattle, WA.
Christopher Hidey, Tuhin Chakrabarty , Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab and Smaranda Muresan.
[pdf] [Code and Data]


1) AMPERSAND: Argument Mining for PERSuAsive oNline Discussions [Oral]
In Proceedings of EMNLP 2019 ,Hong Kong
Tuhin Chakrabarty , Christopher Hidey, Smaranda Muresan, Kathy McKeown and Alyssa Hwang.
[pdf] [Code and Data] [Slides] [Poster] [Talk]

2) IMHO Fine Tuning Improves Claim Detection [Oral]
In Proceedings of NAACL 2019 ,Minneapolis, MN
Tuhin Chakrabarty , Christopher Hidey, Kathy McKeown
[pdf] [Code and Data] [Slides] [Talk]

3) Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks [Oral]
In Proceedings of SIGDIAL 2019 ,Stockholm, Sweden
Siddharth Varia ,Christopher Hidey, Tuhin Chakrabarty .
[pdf] [Code] [Slides]

4) Pay "Attention'' to your Context when Classifying Abusive Language
In Proceedings of 3rd Abusive Language Workshop ,ACL 2019 Florence, Italy.
Tuhin Chakrabarty ,Kilol Gupta, Smaranda Muresan.
[pdf] [Code]

5) The Answer is Language Model Fine-tuning
In Proceedings of the 13th International Workshop on Semantic Evaluation , NAACL-HLT , Minneapolis, USA, June 2019
Tuhin Chakrabarty ,Smaranda Muresan.


1) Robust Document Retrieval and Individual Evidence Modeling for Fact Extraction and Verification
In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER) ,EMNLP ,Brussels ,2018
Tuhin Chakrabarty ,Tariq Alhindi , Smaranda Muresan :-
[pdf] [Code] .


Reviewer : FEVER@EMNLP 2018, FEVER@EMNLP 2019, FEVER@ACL 2020, ALW4@EMNLP 2020, WNUT@EMNLP 2020, ACL 2020, EMNLP 2020 , AACL 2020, STAR-SEM 2020


Email :
tuhinjubcse@gmail.com(PERSONAL GMAIL)
Mobile : +13476306405

alt text alt text alt text


When not doing NLP, I love reading.I love Morissey and The Smiths and feel they are the best band in the world :). I also love taking pictures. See my photography trail on my instagram handle (@bonginnyc). I also sometimes write on love and longing Tuhins blog