Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
11-2021
Abstract
In open-domain dialogue systems, knowledge information such as unstructured persona profiles, text descriptions and structured knowledge graph can help incorporate abundant background facts for delivering more engaging and informative responses. Existing studies attempted to model a general posterior distribution over candidate knowledge by considering the entire response utterance as a whole at the beginning of decoding process for knowledge selection. However, a single smooth distribution could fail to model the variability of knowledge selection patterns over different decoding steps, and make the knowledge expression less consistent. To remedy this issue, we propose an adaptive posterior knowledge selection framework, which sequentially introduces a series of discriminative distributions to dynamically control when and what knowledge should be used in specific decoding steps. The adaptive distributions can also capture knowledge-relevant semantic dependencies between adjacent words to refine response generation. In particular, for knowledge graph-grounded dialogue generation, we further incorporate the adaptive distributions into generative word distributions to help express the knowledge entity words. The experimental results show that our developed methods outperform strong baseline systems by large margins.
Keywords
dialogue generation, knowledge graph, text knowledge, adaptive knowledge selection, posterior distribution over knowledge
Discipline
Numerical Analysis and Scientific Computing | Theory and Algorithms
Research Areas
Data Science and Engineering
Publication
CIKM '21: Proceedings of the 30th ACM International Conference on Information and Knowledge Management, Virtual, November 1-5
First Page
1989
Last Page
1998
ISBN
9781450384469
Identifier
10.1145/3459637.3482314
Publisher
ACM
City or Country
New York
Citation
WANG, Weichao; GAO, Wei; FENG, Shi; CHEN, Ling; and WANG, Daling.
Adaptive posterior knowledge selection for improving knowledge-grounded dialogue generation. (2021). CIKM '21: Proceedings of the 30th ACM International Conference on Information and Knowledge Management, Virtual, November 1-5. 1989-1998.
Available at: https://ink.library.smu.edu.sg/sis_research/6678
Copyright Owner and License
Publisher
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1145/3459637.3482314