Search Results for author: Kshitij Mishra

Found 4 papers, 1 papers with code

Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems

no code implementations Findings (NAACL) 2022 Azlaan Mustafa Samad, Kshitij Mishra, Mauajama Firdaus, Asif Ekbal

Even the most well-intended and reasoned persuasive conversations can fall through in the absence of empathetic connection between the speaker and listener.

Language Modelling Persuasiveness +1

PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation

1 code implementation COLING 2022 Kshitij Mishra, Azlaan Mustafa Samad, Palak Totala, Asif Ekbal

Our experimental results demonstrate that PEPDS increases the rate of persuasive responses with emotion and politeness acknowledgement compared to the current state-of-the-art dialogue models, while also enhancing the dialogue’s engagement and maintaining the linguistic quality.

Persuasiveness

Tabular and Deep Reinforcement Learning for Gittins Index

no code implementations2 May 2024 Harshit Dhankar, Kshitij Mishra, Tejas Bodas

When compared with existing RL algorithms that learn the Gittins index, our algorithms have a lower run time, require less storage space (small Q-table size in QGI and smaller replay buffer in DGN), and illustrate better empirical convergence to the Gittins index.

reinforcement-learning Reinforcement Learning (RL) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.