Avoiding echo-responses in a retrieval-based conversation system

Abstract

Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system’s goal is to find the most appropriate response, rather than the most semantically similar one, this tendency results in low-quality responses. We refer to this challenge as the echoing problem. To mitigate this problem, we utilize a hard negative mining approach at the training stage. The evaluation shows that the resulting model reduces echoing and achieves better results in terms of Average Precision and Recall@N metrics, compared to the models trained without the proposed approach.