Abhinav Ramesh Kashyap

National University of Singapore WING NUS

I am a fourth year PhD student advised by Prof Min-Yen Kan. I also closely collaborate with Devamanyu Hazarika. My research is on Natural Language Processing. I focus on making NLP models robust under different domains. NLP models do not perform well when presented with data from different domains and my focus is on Domain Adaptation for NLP. I am also interested in Scholarly Document Processing.

Previously,

I completed my Masters from the National University of Singapore. My master’s thesis involved extractive summarization specific to restaurant reviews. I was part of the Sensor Enhanced Social Media(SeSaMe) lab with Prof. Mohan Kankanhalli

News

May 13, 2022

Presented our paper “So Different Yet So Alike! Constrained Unsupervised Text Style Transfer” at SSNLP’22

Apr 22, 2022

Recognized as an Outstanding Reviewer for ICLR 2022

Apr 1, 2022

Wrapped up my internship at Amazon.

Feb 24, 2022

Our work “So Different Yet So Alike! Constrained Unsupervised Text Style Transfer” is accepted at ACL.

Oct 1, 2021

Started as an Applied Scientist Intern @ Amazon Science. Excited to work with Mahdi Namazifar

Apr 19, 2021

Presenting our paper at EACL’21 online.

Mar 10, 2021

1 Long Paper accepted at NAACL. We survey domain divergences, their use cases and analyze which divergence is more suitable to predict drops in performance.

Feb 19, 2021

1 Long paper accepted at the AdaptNLP workshop at EACL. We investigate the inherent domain robustness of various kinds of pretrained language models.

Aug 1, 2020

1 short paper accepted at the DocEng with my undergrad student. This is the first attempt to create a ranking system for service contributions of researchers

Aug 1, 2020

1 demo paper accepted at the SDP workshop at EMNLP. We release a new toolkit for scientific document processing.