Papers by Ishaan Grover

Copied to clipboard

Challenge:	Existing approaches to deep learning for open-domain dialogue include training end-to-end models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts and persona of the agent and the user, among others.
Approach:	They propose a probabilistic approach using Markov Random Fields to augment existing deep-learning methods for improved next utterance prediction.
Outcome:	The proposed approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents.