no code implementations • 9 Jan 2024 • Shrey Satapara, Parth Mehta, Debasis Ganguly, Sandip Modha
The recent success in language generation capabilities of large language models (LLMs), such as GPT, Bard, Llama etc., can potentially lead to concerns about their possible misuse in inducing mass agitation and communal hatred via generating fake news and spreading misinformation.
no code implementations • 16 Mar 2023 • Parth Mehta, Kumar Appaiah, Rajbabu Velmurugan
We then incorporate a retransmission based minimum variance distortionless response (MVDR) beamformer with the feedback beamforming setup.
no code implementations • 22 Feb 2023 • Parth Mehta, Agulla Surya Bharath, Kumar Appaiah, Rajbabu Velmurugan, Debasattam Pal
Modern 5G communication systems employ multiple-input multiple-output (MIMO) in conjunction with orthogonal frequency division multiplexing (OFDM) to enhance data rates, particularly for wideband millimetre wave (mmW) applications.
no code implementations • 4 Oct 2021 • Vedant Parikh, Vidit Mathur, Parth Mehta, Namita Mittal, Prasenjit Majumder
Some possible applications of this dataset besides legal document summarization can be in retrieval, citation analysis and prediction of decisions by a particular judge.
no code implementations • 12 Nov 2020 • Sean McGrath, Parth Mehta, Alexandra Zytek, Isaac Lage, Himabindu Lakkaraju
As machine learning (ML) models are increasingly being employed to assist human decision makers, it becomes critical to provide these decision makers with relevant inputs which can help them decide if and how to incorporate model predictions into their decision making.
no code implementations • 7 Sep 2018 • Parth Mehta, Prasenjit Majumder
With an ever growing number of extractive summarization techniques being proposed, there is less clarity then ever about how good each system is compared to the rest.
no code implementations • 13 Feb 2018 • Parth Mehta, Gaurav Arora, Prasenjit Majumder
We propose a new attention based deep learning architecture that jointly learns to identify important content, as well as the cue phrases that are indicative of summary worthy sentences.
no code implementations • 3 Feb 2018 • Parth Mehta, Prasenjit Majumder
In this paper, we describe a category of ensemble systems which use consensus between the candidate systems to build a better meta-summary.