Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy. To this end, we introduce PLATO-K based on two-stage dialogic learning to strengthen internal knowledge memorization and external knowledge exploitation. In the first stage, PLATO-K learns through massive dialogue corpora and memorizes essential knowledge into model parameters. In the second stage, PLATO-K mimics human beings to search for external information and to leverage the knowledge in response generation. Extensive experiments reveal that the knowledge issue is alleviated significantly in PLATO-K with such comprehensive internal and external knowledge enhancement. Compared to the existing state-of-the-art Chinese dialogue model, the overall engagingness of PLATO-K is improved remarkably by 36.2% and 49.2% on chit-chat and knowledge-intensive conversations.
@article{arxiv.2211.00910,
title = {PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation},
author = {Siqi Bao and Huang He and Jun Xu and Hua Lu and Fan Wang and Hua Wu and Han Zhou and Wenquan Wu and Zheng-Yu Niu and Haifeng Wang},
journal= {arXiv preprint arXiv:2211.00910},
year = {2022}
}
Comments
First four authors contributed equally to this work