no code implementations • ICON 2019 • Zishan Ahmad, Deeksha Varshney, Asif Ekbal, Pushpak Bhattacharyya
Extracting related arguments like Time, Place, Casualties, etc., provides a complete picture of the disaster event.
no code implementations • 31 Aug 2023 • Atharvan Dogra, Deeksha Varshney, Ashwin Kalyan, Ameet Deshpande, Neeraj Kumar
The generation of effective latent representations and their subsequent refinement to incorporate precise information is an essential prerequisite for Vision-Language Understanding (VLU) tasks such as Video Question Answering (VQA).
1 code implementation • 16 Nov 2022 • Deeksha Varshney, Aizan Zafar, Niranshu Kumar Behra, Asif Ekbal
The development of conversational agents to interact with patients and deliver clinical advice has attracted the interest of many researchers, particularly in light of the COVID-19 pandemic.
1 code implementation • NAACL 2022 • Deeksha Varshney, Akshara Prabhakar, Asif Ekbal
In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance.
no code implementations • EACL 2021 • Deeksha Varshney, Asif Ekbal, Pushpak Bhattacharyya
We employ multi-task learning to predict the emotion label and to generate a viable response for a given utterance using a common encoder with multiple decoders.