Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

Abstract

Open-domain human-computer conversation has attracted much attention in the field of NLP. Contrary to rule- or template-based domain-specific dialog systems, open-domain conversation usually requires data-driven approaches, which can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (called a query) in a large database, and return a reply that best matches the query. Generative approaches, typically based on recurrent neural networks (RNNs), can synthesize new replies, but they suffer from the problem of generating short, meaningless utterances. In this paper, we propose a novel ensemble of retrieval-based and generation-based dialog systems in the open domain. In our approach, the retrieved candidate, in addition to the original query, is fed to an RNN-based reply generator, so that the neural model is aware of more information. The generated reply is then fed back as a new candidate for post-reranking. Experimental results show that such ensemble outperforms each single part of it by a large margin.

References in corpus (4)

• ADADELTA: An Adaptive Learning Rate Method
• Neural Responding Machine for Short-Text Conversation
• A Hierarchical Neural Autoencoder for Paragraphs and Documents
• An Information Retrieval Approach to Short Text Conversation

Cited by in corpus (12)

• Neural Language Generation: Formulation, Methods, and Evaluation
• Say What I Want: Towards the Dark Side of Neural Dialogue Models
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Keep CALM and Explore: Language Models for Action Generation in Text-based Games
• An Enhanced Knowledge Injection Model for Commonsense Generation
• Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
• Text Generation with Exemplar-based Adaptive Decoding
• Retrieval-based Goal-Oriented Dialogue Generation
• Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
• Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
• Data-Efficient Methods for Dialogue Systems
• Augmenting Machine Learning with Information Retrieval to Recommend Real Cloned Code Methods for Code Completion