Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
This work addresses the problem of generating informative and fluent dialogues in AI systems, representing an incremental improvement by adapting existing techniques from a related task.
The paper tackles the challenge of incorporating commonsense knowledge into open-domain dialogue systems by proposing TransDG, a model that transfers abilities from knowledge base question answering to improve dialogue generation, resulting in robust superiority over compared methods on two benchmark datasets.
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.