Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
arXiv:1912.07491
Abstract
Neural network models usually suffer from the challenge of incorporating commonsense knowledge into the open-domain dialogue systems. In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. In addition, we propose a response guiding attention and a multi-step decoding strategy to steer our model to focus on relevant features for response generation. Experiments on two benchmark datasets demonstrate that our model has robust superiority over compared methods in generating informative and fluent dialogues. Our code is available at https://github.com/siat-nlp/TransDG.
Accepted by AAAI-2020
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Large-scale Simple Question Answering with Memory Networks
- Deep Reinforcement Learning for Dialogue Generation
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
- Improved Neural Relation Detection for Knowledge Base Question Answering