Tuhin Chakrabarty, Computer Science Ph.D. Student, Columbia University

**Tuhin Chakrabarty**
Ph.D. Student in CS @ Columbia

Hire me! I am on the academic and industry job market.

Please find my research statement

I am a final year PhD candidate 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. My additional thesis committee members are Kathleen McKeown, Yejin Choi, Violet Peng and Lydia Chilton.My research is supported by the Columbia Center of Artificial Intelligence & Technology (CAIT) & Amazon Science Ph.D. Fellowship. During 2021-2022, I was a Computational Journalism fellow at NYTimes R&D. My research interests are broadly in Natural Language Processing and Machine Learning, with a special focus on Human-Centered Methods for Understanding, Generation, and Evaluation of Creativity. My overarching research question centers around how we can align models for creative tasks. I specifically focus on the following questions:

1) Can models understand and explain/interpret creative language? (EMNLP 2022, TACL 2022)
2) Can models generate creative text such as Sarcasm, Simile, Metaphor? (ACL 2020, EMNLP 2020, NAACL 2021)
3) Can models maintain semantic faithfulness when translating creative text? (EMNLP 2021)
4) How can we design better ways to evaluate long-form creative writing by drawing on technical skills from computer science and design in combination with other disciplines, including the humanities, to expand the communities? (CHI 2024 [In preparation])
5) Can humans effectively collaborate with LLMs that understand their intent and align with their expectations to produce creative content? (Under submission)
6) Can LLM's be helpful in aiding models trained on modalities other than language for creative tasks at hand? (ACL 2023, EMNLP 2023)
As an act of giving back to the community, I am happy to advise undergrads and master's students about grad school applications and/or how to get involved in NLP research. If you are at Columbia and have experience with Reinforcement Learning or Vision and Language and want to work with me, please send me an email. Before you email me, please make sure we have overlapping research interests.I mentored the following students:

Arkadiy Saakyan (Columbia Undergrad now PhD student)

Kanishk Singh (Columbia Undergrad)

Aadit Trivedi (Georgia Tech Undergrad)

Here are some metaphoric illustrations from my upcoming paper

Media

The Hollywood Reporter Why AI Isn’t Funny — At Least Not Yet
The New York Times R&D Generating Open-Ended Questions from News Articles

Hire me! I am on the academic and industry job market.

Media

Recent News

Education

Professional Experience

Papers

2023

Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers

Art or Artifice? Large Language Models and the False Promise of Creativity

Learning to Follow Object-Centric Image Editing Instructions Faithfully

NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly

I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors

2022

Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing

FLUTE: Figurative Language Understanding through Textual Explanations

Fine-tuned Language Models are Continual Learners

Multitask Instruction-based Prompting for Fallacy Detection

CONSISTENT: Open-Ended Question Generation From News Articles

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

2021

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

Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models

Metaphor Generation with Conceptual Mappings

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

Figurative Language in Recognizing Textual Entailment

ENTRUST: Argument Reframing with Language Models and Entailment

MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

Identifying Distributional Perspective Differences from Colingual Groups

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

2020

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

Content Planning for Neural Story Generation with Aristotelian Rescoring

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

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

2019

AMPERSAND: Argument Mining for PERSuAsive oNline Discussions

IMHO Fine Tuning Improves Claim Detection

Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks

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

The Answer is Language Model Fine-tuning

2018

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

Contact

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

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