Dialogue engines that incorporate different types of agents to converse with humans are popular. However, conversations are dynamic in the sense that a selected response will change the conversation on-the-fly, influencing the subsequent utterances in the conversation, which makes the response selection a challenging problem. We model the problem of selecting the best response from a set of responses generated by a heterogeneous set of dialogue agents by taking into account the conversational history, and propose a \emph{Neural Response Selection} method. The proposed method is trained to predict a coherent set of responses within a single conversation, considering its own predictions via a curriculum training mechanism. Our experimental results show that the proposed method can accurately select the most appropriate responses, thereby significantly improving the user experience in dialogue systems.
@article{arxiv.2005.03066,
title = {Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents},
author = {Asir Saeed and Khai Mai and Pham Minh and Nguyen Tuan Duc and Danushka Bollegala},
journal= {arXiv preprint arXiv:2005.03066},
year = {2020}
}