Ankita Rajaram Naik

Ankita Rajaram Naik

M.S. in Computer Science

University of Massachusetts Amherst

Biography

I'm a final year master student at the University of Massachusetts Amherst with 4+ years of experience working in Natural Language Processing.

My most recent projects are focused on Knowledge Graph Reasoning for Question Answering and Graph Completion; Retrieval models for knowledge bases and tables; and Biomedical Applications of NLP with research publications in leading conference such as AAAI, NAACL and ICML. At UMass Amherst, I primarily worked with Prof. Andrew Mccallum and Rajarshi Das at Information Extraction and Synthesis Lab (IESL). I also interned with the Knowledge Induction Group at IBM Research AI under the mentorship of Michael Glass and Alfio Gloizzo. Moreover, I have also worked with researchers at GE Healthcare and Walmart while receiving my MS in Computer Science.

Before starting my masters, I finished my undergraduate at IIT Madras in India. Just after my undergraduate, I worked at ZS Associates as a Data Scientist for 2 years where I focused on Biomedical problems such as disease progression modeling, sales targeting and clinical trial optimizations.

Looking for full-time positions in Natural Language Processing. Download my resumé.

Interests
  • Knowledge Representation
  • Knowledge Graph Reasoning
  • Biomedical Natural Language Processing
Education
  • M.S. in Computer Science, 2022

    University of Massachusetts Amherst

  • BTech in Metallurgical Engineering (Minor in Operations Research), 2017

    Indian Institute of Technology Madras

Publications

(2022). Knowledge Base Question Answering by Case-based Reasoning over Subgraphs. In ICML 2022.

PDF Cite Code

(2022). Re2G: Retrieve, Rerank, Generate. In NAACL 2022.

PDF Cite

(2021). Shallow-uwnet: Compressed model for underwater image enhancement (student abstract). In AAAI 2021.

PDF Cite Code Poster

(2020). Leveraging Knowledge Distillation for Efficient on-device Deployment of Deep Learning Models in Medical Imaging. In SIIM 2020.

PDF Cite

Experience

 
 
 
 
 
Research Intern
May 2021 – Present Yorktown Heights, NY
Worked with the Knowledge Induction Team in Summer 2021 on a retrieval-based language model for Fact Verification task. The Retrieval Augmented Generation (RAG) and Dense Passage Retrieval (DPR) based model (Re2G) is the current state-of-art for multiple tasks including Fact Verification on KILT dataset created by Facebook AI. The research is published in NAACL 2022.

Currently, I am working with the group on a Table Augmentation task. We are developing a neural retrieval (Dense Passage Retrieval) and span selection based model for cell filling on WikiTables Corpus. Moreover, we are working on a self-supervised architecture for improving DPR training. See More ..
 
 
 
 
 
Graduate Student Researcher
Mar 2021 – May 2022 Amherst, MA
Worked on a knowledge base question answering project. We developed a semi-parametric model which leverages structural similarity between local neighborhoods of subgraphs. Reasoning paths obtained from these subgraphs created around query entities were used for finding the answer entities. The research extensively focuses on case-based reasoning approach over localized subgraphs. This research is published in ICML 2022.
 
 
 
 
 
Machine Learning Intern
May 2020 – Jul 2020 Bentonville, Arkansas
Worked with the Global People Analytics Team at Walmart Inc. for setting up a Fairness algorithm for Walmart Store hiring across the United States. Implemented a fairness algorithm using PyTorch and redesigned its loss function to improve performance.
 
 
 
 
 
Graduate Researcher
Jan 2020 – May 2020 Remote
Worked on utilizing Knowledge Distillation framework to deploy a deep CNN model on-device for carrying out disease detection from X-Ray images. The finding from the semester project were published in Conference on Machine Intelligence in Medical Imaging at Society for Imaging Informatics in Medicine. See More ..
 
 
 
 
 
Data Scientist
Jul 2017 – Jul 2019 Pune, India
ZS is a healthcare consulting company which devises ML-oriented solutions for Sales and Marketing problems of Pharma companies like Amgen, Novartis, Pfizer.
At the Data Science Lab at ZS Associates, I have worked on gamut of projects ranging from application of NLP and Deep Learning techniques for social media data (Twitter), patient medical history data to using statistical machine learning for dynamic sales targeting and clinical trial optimizations. See More ..

Contact