Shikha Bordia

Professional Background

I am working as NLP Research Engineer at Verisk Analytics on Muti-hop reasoning, Information Extraction and Natural Language Generation in NLP . I completed Master’s in Computer Science from New York University’s Courant Institute of Mathmatical Sciences in 2019. I was advised by Prof. Samuel R.Bowman. I was also part of ML^2 Group at CILVR Lab. Broadly, my research interests are machine learning and natural language processing.

Outside of NLP, I modeled Structured Finance products such as CBOs, CLOs, Synthetic Structures for over 3.5 years at Deutsche Bank after graduating from Indian Institute of Technology, Kharagpur(2007 - 2011). I was instrumental in Industry Buying’s growth from 30 to over 300 employees and from series A to series B funding in a brief span of 9 months in year 2015. I have also worked as data science consultant for multiple clients in Healthcare, Telecom and Retail Industry in US.

Publications/Projects

HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification
Yichen Jiang*, Shikha Bordia*, Zheng Zhong, Charles Dognin, Maneesh Singh, Mohit Bansal
Findings of EMNLP 2020
[Paper][HoVer Leaderboard]

Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs
Alex Warstadt*, Yu Cao*, Ioana Grosu*, Wei Peng*, Hagen Blix*, Yining Nie*, Anna Alsop*, Shikha Bordia*, Haokun Liu*, Alicia Parrish*, Sheng-Fu Wang*, Jason Phang*, Anhad Mohananey*, Phu Mon Htut*, Paloma Jeretic* and Samuel R. Bowman.
Proceedings of EMNLP 2019
[Paper][Slides][Talk]

Identifying and Reducing Gender Bias in Word-Level Language Models
Shikha Bordia and Samuel R. Bowman
NAACL, Student Research Workshop, 2019
[Paper][Slides][Poster][Talk]

On Measuring Social Biases in Sentence Encoders
Chandler May, Alex Wang, Shikha Bordia, Samuel R. Bowman, Rachel Rudinger
NAACL 2019.
[Paper][Talk]

Do Attention Heads in BERT Track Syntactic Dependencies?
Phu Mon Htut*, Jason Phang*, Shikha Bordia*, and Samuel R. Bowman.
Natural Language, Dialog and Speech (NDS) Symposium, The New York Academy of Sciences. 2019. (Extended Abstract)
[Paper][Poster][Blog]

Contributed to jiant
jiant is a work-in-progress software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks.