• Sept 2022: Shifting to Vancouver and starting my Masters (Thesis) in Computer Science at UBC Vancouver. I will be working with Prof. Vered Shwartz.
  • Aug 2021: Interviewed Dr. Sebastian Ruber as part of NLP Panel Discussion at NeuralSpace. Link can be found here on YouTube
  • Aug 2021: Joining DeCLaRe Lab as a Research Associate. Thank you Prof. Soujanya for the opportunity and NeuralSpace for agreeing to the collaboration
  • Jul 2021: Joining NeuralSpace as an Applied Research Scientist. So excited for this opportunity.
  • June 2021: Attending my first NAACL conference as a volunteer! Thrilled to meet so many volunteers.
  • Dec 2020: Presenting my poster at Women in Machine Learning Workshop at NeurIPS 2020!
  • July 2020: I just graduated (virtually) with a Bachelor's Degree in Computer Science and Engineering and minor in Mathematics from Shiv Nadar University, India!
  • June 2020: I joined MIDAS Lab, IIIT Delhi fulltime as a Research Assistant! Excited to work on some amazing projects and burn the midnight oil!
  • Jan 2020: I joined MIDAS Lab, IIIT Delhi as a Research Intern for five months! Excited to collaborate with Prof. Junyi Jessy Li for my Bachelor Thesis Project.
  • Jan 2020: Attending ACM CoDS-COMAD Conference 2020 at Indian School of Business (ISB), Hyderabad India from 5-7 January 2020.
  • Dec 2019: Presented my research work at ICON 2019 (International Conference on Natural Langauge Processing) conference. This is a result of my internship at SERC IIIT Hyderabad
  • Nov 2019: Presented my work at International Conference on Data Mining (A* conference) at Beijing, China! Thank you Prof. Rajiv for giving me the opportunity to lead the project and collaborating with Dr. Debanjan Mahata.
  • Aug 2019: Won Honorable Mention Award of 2019 ICDM/ICBK Knowledge Graph Contest to be held at Beijing, China on 10th Novemeber 2019.

Selected Publications

Knowledge-grounded dialogue systems tend to generate responses based on information provided in grounding corpora. Though there has been recent progress in training end-to-end informative systems that mimic human language at the linguistic level, yet there are no controls available that ensure they are ...

This paper is a contribution to the Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC) 2021 shared task. Social media today is a hotbed of toxic and hateful conversations, in various languages. Recent news reports have shown that current models struggle to automatically identify hate posted in minority ...

Automatic scoring engines have been used for scoring approximately fifteen million test-takers in just the last three years. This number is increasing further due to COVID-19 and the associated automation of education and testing. Despite such wide usage, the AI-based testing literature of these "intelligent" models is highly lacking. Most of the papers proposing new models rely ...

Recent studies in speech perception have been closely linked to fields of cognitive psychology, phonology, and phonetics in linguistics. During perceptual attunement, a critical and sensitive developmental trajectory has been examined in bilingual and monolingual infants where they can best discriminate common phonemes. In this paper, we compare and identify these cognitive aspects ...

Increased internet bandwidth at low cost is leading to the creation of large volumes of unstructured data. This data explosion opens up opportunities for the creation of a variety of data-driven intelligent systems, such as the Semantic Web. Ontologies form one of the most crucial layers of semantic web, and the extraction and enrichment of ontologies given this data explosion becomes an inevitable research problem. In this paper, we survey the ...


Natural Language Processing (NLP) applications are now ubiquitous and used by millions of individuals worldwide on a daily basis. Nevertheless, these applications can be overwhelmingly brittle and biased. For example, it has been seen that the accuracy of syntactic parsing models drops by at least 20 percent on African-American vernacular English when compared to textbook-like English (how it is commonly spoken by the more privileged class of Americans). Further, sentiment analyzers fail on language originating from different time periods, question-answering systems fail on British English, conversational assistants struggle to interact with millions of elderly people with speech disabilities, and hate speech detection systems are biased and more likely to classify language from specific demographics incorrectly as offensive. In short, NLP models and applications work well only for a minority of the population, effectively excluding a significant majority that uses such applications exactly as often. It is shocking to see that roughly 6500 languages are spoken in the world today, however, the advancement in NLP in academia and industry focuses on a minuscule subset...