RefNet: A Reference-aware Network for Background Based Conversation
arXiv:1908.06449
Abstract
Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods for BBCs are able to generate more informative responses, they either cannot generate natural responses or have difficulty in locating the right background information. In this paper, we propose a Reference-aware Network (RefNet) to address the two issues. Unlike existing methods that generate responses token by token, RefNet incorporates a novel reference decoder that provides an alternative way to learn to directly cite a semantic unit (e.g., a span containing complete semantic information) from the background. Experimental results show that RefNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that RefNet can generate more appropriate and human-like responses.
arXiv commentAccepted to AAAI 2020 (Oral)
References in corpus (19)
- Sequence to Sequence Learning with Neural Networks
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Bidirectional Attention Flow for Machine Comprehension
- A Neural Conversational Model
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- Topic Aware Neural Response Generation
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
- Neural Machine Reading Comprehension: Methods and Trends
- Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
- Improving Background Based Conversation with Context-aware Knowledge Pre-selection
- Towards Exploiting Background Knowledge for Building Conversation Systems
- A Dataset for Document Grounded Conversations
- Extending Neural Generative Conversational Model using External Knowledge Sources