`

Timezone: »

 
Poster
Zero-Resource Knowledge-Grounded Dialogue Generation
Linxiao Li · Can Xu · Wei Wu · YUFAN ZHAO · Xueliang Zhao · Chongyang Tao

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #972

While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain. To overcome the data challenge and reduce the cost of building a knowledge-grounded dialogue system, we explore the problem under a zero-resource setting by assuming no context-knowledge-response triples are needed for training. To this end, we propose representing the knowledge that bridges a context and a response and the way that the knowledge is expressed as latent variables, and devise a variational approach that can effectively estimate a generation model from independent dialogue corpora and knowledge corpora. Evaluation results on three benchmarks of knowledge-grounded dialogue generation indicate that our model can achieve comparable performance with state-of-the-art methods that rely on knowledge-grounded dialogues for training, and exhibits a good generalization ability over different datasets.

Author Information

Linxiao Li (Peking University)
Can Xu (microsoft)
Wei Wu (Meituan-Dianping Group)
YUFAN ZHAO (Microsoft)
Xueliang Zhao (Peking University)
Chongyang Tao (Microsoft)

More from the Same Authors