Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
arXiv:1809.05296
Abstract
For dialogue response generation, traditional generative models generate responses solely from input queries. Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways. Consequentially, those models tend to output generic and dull responses, impeding the generation of informative utterances. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. When generating a response for a current query, similar dialogues retrieved from the entire training data are considered as an additional knowledge source. While this may harvest massive information, the generative models could be overwhelmed, leading to undesirable performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-then-response paradigm. At first, a skeleton is generated by revising the retrieved responses. Then, a novel generative model uses both the generated skeleton and the original query for response generation. Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses.
arXiv commentaccepted to NAACL2019
References in corpus (9)
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- A Neural Conversational Model
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- Topic Aware Neural Response Generation
- An Information Retrieval Approach to Short Text Conversation
- Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
- Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
- Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning
- Retrieve and Refine: Improved Sequence Generation Models For Dialogue