Tuhin Chakrabarty

Ph.D. Student in CS @ Columbia

Hey there!


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 Smaranda Muresan. I also work with Violet Peng at UCLA PLUS Lab. In the past I worked with Kathleen Mckeown. My research interests are broadly in Natural Language Processing and Machine Learning, with special focus in Figurative Language. Despite the ubiquity of figurative language across various forms of speech and writing, the vast majority of NLP research focuses primarily on literal language. Figurative language is challenging because of its implicit nature. I specifically focus on the following questions 1) Can LLMs understand/interpret them? 2) Can computers generate figurative language such as Sarcasm, Simile, Metaphor. 3) Can computers maintain the figurative aspects of language when translating it between language pairs. Prior to joining Grad school I was an engineer at UBER. For more information about me, see my CV or contact me.


My introduction to NLP was through my friend Chris Hidey who mentored me and helped me write several papers. As an act of giving back to the community, I am happy to advise undergrads and master students about grad school applications and/or how to get involved in NLP research. If you are at Columbia and want to work with me , please send me an email. I mentored the following students:
I am looking for part time CPT (<=20 hr /week) opportunities in ML /NLP opportunities. Please reach out to me

Fun fact about me :




Recent News

  • New Preprint on Commonsense for Figurative Language Interpretation which are less compositional in nature
  • 2 first author papers acepted to EMNLP 2021
  • 2 long papers accepted to ACL 2021 main conference and 1 short paper accepted to Findings of ACL
  • 2 long papers accepted to NAACL 2021
  • I am a NYTimes R&D fellow starting Fall 2021
  • Our ACL 2020 Paper Deseption was taught in the Misinformation Detection Lecture(11/06) at UIUC "Information Extraction and Knowledge Acquisition" [Details here]

Education

2017-now
Columbia University

Ph.D. in Computer Science

2017-2019
Columbia University

M.S. in Computer Science

2010-2014
Jadavpur University

Bachelors of Engineering in Computer Science

Professional Experience

2021
Mosaic (Machine Commonsense Team)

Research Intern (PhD)

2018
Amazon Alexa

Applied Scientist Intern

2016-2017
UBER (Revenue Team)

Machine Learning Engineer




For more details, please see my full CV (PDF).

Papers




2021


It’s not Rocket Science: Interpreting Figurative Language in Narratives

Tuhin Chakrabarty , Yejin Choi and Vered Shwartz
Under Submission
Tags: Figurative Language, Multiword Expression, Commonsense

Don't Go Far Off: An Empirical Study on Neural Poetry Translation

Tuhin Chakrabarty , Arkadiy Saakyan and Smaranda Muresan
In Proceedings of EMNLP 2021 ,Punta Cana, Dominican Republic.
Tags: Machine Translation, Figurative Language, Faithfulness

Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models

Tuhin Chakrabarty , Aadit Trivedi and Smaranda Muresan
In Proceedings of EMNLP 2021 ,Punta Cana, Dominican Republic.
Tags: Creative Language Generation, Implicit Reasoning, Discourse aware Commonsense

Metaphor Generation with Conceptual Mappings

Kevin Stowe , Tuhin Chakrabarty , Nanyun Peng, Smaranda Muresan and Iryna Gurevych
In Proceedings of ACL 2021 ,Bangkok, Thailand.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

COVID-Fact: Fact Extraction and Verification of Real-World Claims concerning the COVID-19 pandemic

Arkadiy Saakyan , Tuhin Chakrabarty and Smaranda Muresan
In Proceedings of ACL 2021 ,Bangkok, Thailand.
Tags: Language Generation, Argumentation, Fact Checking

Figurative Language in Recognizing Textual Entailment

Tuhin Chakrabarty , Debanjan Ghosh, Adam Poliak and Smaranda Muresan
In Findings of ACL 2021 ,Bangkok, Thailand.
Tags: Figurative Language, Textual Entailment

ENTRUST: Argument Reframing with Language Models and Entailment

Tuhin Chakrabarty , Christopher Hidey and Smaranda Muresan
In Proceedings of NAACL 2021 ,Mexico City, Mexico.
Tags: Language Generation, Argumentation

MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

Tuhin Chakrabarty ,Xurui Zhang, Smaranda Muresan and Nanyun Peng
In Proceedings of NAACL 2021 ,Mexico City, Mexico.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

Identifying Distributional Perspective Differences from Colingual Groups

Yufei Tian , Tuhin Chakrabarty , Fred Morstatter, Nanyun Peng
In Proceedings of SocialNLP@NAACL 2021 ,Mexico City, Mexico.
Tags: Discourse Understanding, Argumentation

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

Sarik Ghazarian, Zixi Liu, Tuhin Chakrabarty ,Xuezhe Ma, Aram Galstyan, Nanyun Peng
In Proceedings of NAACL 2021 (Demo Track) ,Mexico City, Mexico.
Tags: Controllable Language Generation, Dialogue Generation, Knowledge Grounding

2020


Generating similes effortlessly like a Pro : A Style Transfer Approach for Simile Generation

Tuhin Chakrabarty , Smaranda Muresan and Nanyun Peng
In Proceedings of EMNLP 2020 ,Punta Cana, Dominican Republic.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

Content Planning for Neural Story Generation with Aristotelian Rescoring

Seraphina Goldfarb-Tarrant, Tuhin Chakrabarty , Ralph Weischedel and Nanyun Peng
In Proceedings of EMNLP 2020 ,Punta Cana, Dominican Republic.
Tags: Creative Language Generation, Narrative, Computational Creativity

R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

Tuhin Chakrabarty , Debanjan Ghosh, Smaranda Muresan and Nanyun Peng
In Proceedings of ACL 2020 ,Seattle, WA.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking

Christopher Hidey, Tuhin Chakrabarty , Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab and Smaranda Muresan.
In Proceedings of ACL 2020 ,Seattle, WA.
Tags: Fact Checking, Discourse, Argumentation

2019

AMPERSAND: Argument Mining for PERSuAsive oNline Discussions

Tuhin Chakrabarty , Christopher Hidey, Smaranda Muresan, Kathy McKeown and Alyssa Hwang.
In Proceedings of EMNLP 2019 ,Hong Kong.
Tags: Discourse, Argumentation

IMHO Fine Tuning Improves Claim Detection

Tuhin Chakrabarty , Christopher Hidey and Kathy McKeown.
In Proceedings of NAACL 2019 ,Minneapolis, MN.
Tags: Discourse, Argumentation

Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks

Siddharth Varia ,Christopher Hidey, Tuhin Chakrabarty
In Proceedings of SIGDIAL 2019 ,Stockholm, Sweden
[PDF] [Code] [Slides]
Tags: , Discourse

Pay "Attention'' to your Context when Classifying Abusive Language

Tuhin Chakrabarty ,Kilol Gupta, Smaranda Muresan.
In Proceedings of 3rd Abusive Language Workshop ,ACL 2019 Florence, Italy.
[PDF] [Code]
Tags: NLP For Social Good

The Answer is Language Model Fine-tuning

Tuhin Chakrabarty ,Smaranda Muresan.
In Proceedings of the 13th International Workshop on Semantic Evaluation , NAACL-HLT , Minneapolis, USA, June 2019
[PDF]
Tags: Discourse, Argumentation

2018


Robust Document Retrieval and Individual Evidence Modeling for Fact Extraction and Verification

Tuhin Chakrabarty ,Tariq Alhindi , Smaranda Muresan
In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER) ,EMNLP ,Brussels ,2018
[PDF] [Code]

Contact


E-mail: <x>@cs.columbia.edu, where x=tuhin.chakr.
The Interchurch Center 61 Claremont Avenue, Data Science Institute , 3rd floor (map).