Papers by Hitesh Golchha
Courteously Yours: Inducing courteous behavior in Customer Care responses using Reinforced Pointer Generator Network (N19-1)
Copied to clipboard
| Challenge: | In order to ensure customer satisfaction and retention, it is imperative for customer care agents and chatbots to be cordial and emphatic to the customer. |
| Approach: | They propose a deep learning framework that automatically transforms neutral customer care responses into courteous replies by stylistic transfer. |
| Outcome: | The proposed model can generate courteous expressions consistent with the emotional state of the customer while preserving the content. |
Language Guided Exploration for RL Agents in Text Environments (2024.findings-naacl)
Copied to clipboard
| Challenge: | Real-world sequential decision making is characterized by sparse rewards and large decision spaces. |
| Approach: | They introduce a language-based framework that provides decision-level guidance to an RL agent. |
| Outcome: | The proposed framework outperforms vanilla RL agents on ScienceWorld in 2022. |