Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
This addresses the challenge of generating more natural and contextually appropriate responses in conversational AI, though it appears incremental as it builds on existing re-ranking and event modeling techniques.
The paper tackled the problem of selecting coherent and diverse responses in dialogue systems by re-ranking candidates based on event causality relations, using a Role Factored Tensor Model for event representation. Experimental results showed improvements in coherency and dialogue continuity.
We propose a novel method for selecting coherent and diverse responses for a given dialogue context. The proposed method re-ranks response candidates generated from conversational models by using event causality relations between events in a dialogue history and response candidates (e.g., ``be stressed out'' precedes ``relieve stress''). We use distributed event representation based on the Role Factored Tensor Model for a robust matching of event causality relations due to limited event causality knowledge of the system. Experimental results showed that the proposed method improved coherency and dialogue continuity of system responses.