Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents

TL;DR

This paper introduces a neural response selection method for dialogue systems that effectively chooses the most appropriate response from multiple agents by considering conversational context and using curriculum training.

Contribution

It presents a novel weakly-supervised neural approach for response selection that models conversational history and employs curriculum training to improve accuracy.

Findings

Significantly improves response selection accuracy

Enhances user experience in dialogue systems

Effective in selecting contextually coherent responses

Abstract

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.