1 code implementation • 17 Jan 2024 • Sabariswaran Mani, Abhranil Chandra, Sreyas Venkataraman, Adyan Rizvi, Yash Sirvi, Soumojit Bhattacharya, Aritra Hazra
The Train-Offline-Test-Online (TOTO) Benchmark provides a well-curated open-source dataset for offline training comprised mostly of expert data and also benchmark scores of the common offline-RL and behaviour cloning agents.
no code implementations • 12 Oct 2022 • Saptarashmi Bandyopadhyay, Shraman Pal, Hao Zou, Abhranil Chandra, Jordan Boyd-Graber
We demonstrate that in a low resource setting, using the generated data improves the QA performance over the baseline system on both NQ and QB data.
1 code implementation • 25 Dec 2021 • Nithish Kannen, Divyanshu Sheth, Abhranil Chandra, Shubhraneel Pal
Acronyms and long-forms are commonly found in research documents, more so in documents from scientific and legal domains.
1 code implementation • 9 Oct 2021 • Varun Madhavan, Aditya Girish Pawate, Shraman Pal, Abhranil Chandra
Cognitively inspired Natural Language Pro-cessing uses human-derived behavioral datalike eye-tracking data, which reflect the seman-tic representations of language in the humanbrain to augment the neural nets to solve arange of tasks spanning syntax and semanticswith the aim of teaching machines about lan-guage processing mechanisms.