End-to-End Deep Reinforcement Learning for Conversation Disentanglement
- Karan Bhukar
- Dinesh Raghu
- et al.
- AAAI 2023
I am a Research Scientist in the Conversational AI group at IBM Research, New Delhi. My primary interests are in Natural Language Processing, Machine Learning, and Information Extraction. At IBM, I work on building deep learning models for learning open-domain and task-oriented dialogs. I also contribute to IBM Watson Assistant’s Language Understanding codebase. I contributed to the dictionary based entity extractors, misspelt entity extractor and actions runtime.
I am also a part-time PhD student in Computer Science at the Indian Institute of Technology, Delhi. At IIT Delhi, I work with Prof.Mausam on generalisation of end-to-end task-oriented dialogs to unseen knowledge and reducing the cost involved in learning end-to-end task-oriented dialogs.