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

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.

References in corpus (11)

• Distributed Representations of Words and Phrases and their Compositionality
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Neural Conversational Model
• Regularizing and Optimizing LSTM Language Models
• Passage Re-ranking with BERT
• Assessing BERT's Syntactic Abilities
• A Deep Reinforcement Learning Chatbot
• An Information Retrieval Approach to Short Text Conversation
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
• Deep Neural Network for Learning to Rank Query-Text Pairs