Generative commonsense knowledge subgraph retrieval for open-domain dialogue response generation

Sixing Wu, Jiong Yu, Jiahao Chen, Wei Zhou

Abstract: Highlights•We propose a novel TiLM for commonsense knowledge-ground dialogue response generations.•TiLM can generate high-quality knowledge subgraphs preserving structural information.•TiLM improves the performance without introducing more parameters.•Extensive experiments on two datasets have verified the effectiveness of TiLM.