# Avoiding Echo-Responses in a Retrieval-Based Conversation System

arXiv: https://arxiv.org/abs/1712.05626 · HTML: https://mlsanity.com/paper/1712.05626/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2017.

## Built on by (most cited first, 2 of 2)

- [ValueNet: A New Dataset for Human Value Driven Dialogue System](https://mlsanity.com/paper/2112.06346/) (2021)
- [Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize](https://mlsanity.com/paper/2303.04953/) (2023)

## Abstract (arXiv)

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.