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

**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.My research is supported by the Columbia Center of Artifical Intelligence & Technology (CAIT) & Amazon Science Ph.D. Fellowship. I also work with Violet Peng at UCLA PLUS Lab and He He at NYU ML² .My research interests are broadly in Natural Language Processing and Machine Learning, with special focus in Computational Creativity.My overarching research question centers around how we can use large language models for creativity.I specifically focus on the following questions

1) Can LLMs understand and explain/interpret creative language? (Under Submission, TACL 2022)
2) Can LLMs generate creative text such as Sarcasm, Simile, Metaphor, Stories? (ACL 2020, EMNLP 2020, NAACL 2021)
3) Can LLMs maintain semantic faithfulness when translating creative text? (EMNLP 2021).
4) Can LLMs keep learning new aspects of creativity without forgetting knowledge about the world (Under Submission)
5) Can humans effectively collaborate with LLMs to produce creative content. (Under Submission)

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:

Arkadiy Saakyan (Columbia Undergad)

Aadit Trivedi (Georgia Tech Undergad)

If you are enrolled for Semantic Representations for NLP, here are my office hours:

Hey there!

Recent News

Education

Professional Experience

Papers

2022

FLUTE: Figurative Language Understanding and Textual Explanations

Continual-T0: Progressively Instructing 50+ Tasks to Language Models Without Forgetting

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).