no code implementations • WNUT (ACL) 2021 • Aman Priyanshu, Aleti Vardhan, Sudarshan Sivakumar, Supriti Vijay, Nipuna Chhabra
The increasing use of social media sites in countries like India has given rise to large volumes of code-mixed data.
no code implementations • 25 Jul 2023 • Shripad V. Deshmukh, Srivatsan R, Supriti Vijay, Jayakumar Subramanian, Chirag Agarwal
In this work, we present COUNTERPOL, the first framework to analyze RL policies using counterfactual explanations in the form of minimal changes to the policy that lead to the desired outcome.
no code implementations • 24 May 2023 • Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu, FatemehSadat Mireshghallah
More specifically, we find that when ChatGPT is prompted to summarize cover letters of a 100 candidates, it would retain personally identifiable information (PII) verbatim in 57. 4% of cases, and we find this retention to be non-uniform between different subgroups of people, based on attributes such as gender identity.
no code implementations • 16 Nov 2022 • Supriti Vijay, Aman Priyanshu
Vocalization of such information has allowed the investigation and identification of criminals.
1 code implementation • 14 Nov 2022 • Aman Priyanshu, Supriti Vijay
Downstream training for keyword extractors is a lengthy process and requires a significant amount of data.
1 code implementation • 28 Jun 2022 • Supriti Vijay, Aman Priyanshu
With increasing applications in areas such as biomedical information extraction pipelines and social media analytics, Named Entity Recognition (NER) has become an indispensable tool for knowledge extraction.
no code implementations • 7 Sep 2021 • Aman Priyanshu, Aleti Vardhan, Sudarshan Sivakumar, Supriti Vijay, Nipuna Chhabra
The increasing use of social media sites in countries like India has given rise to large volumes of code-mixed data.