Lai, Peichao, Ye, Feiyang, Fu, Yang-Geng, Chen, Zhiwei, Wu, Yingjie, Wang, Yilei and Chang, Victor (2024). CogNLG: Cognitive Graph for KG-to-text Generation. Expert Systems, 41 (1),
Abstract
Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large-scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG-to-text generation tasks. Our CogNLG is implemented based on the dual-process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.
Publication DOI: | https://doi.org/10.1111/exsy.13461 |
---|---|
Divisions: | College of Business and Social Sciences > Aston Business School > Operations & Information Management College of Business and Social Sciences > Aston Business School |
Funding Information: | Prof Wang's work is supported by the Natural Science Foundation of Fujian Province, PR China (2022J01120); the Innovation Platform for Academician of Hainan Province (YSPTZX202145); Fujian Province Industrial Guiding Project (2022H0012); Major Special Pro |
Additional Information: | © 2023 The Authors. Expert Systems published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
Uncontrolled Keywords: | KG-to-text,cognitive graph,natural language generation,Artificial Intelligence,Theoretical Computer Science,Control and Systems Engineering,Computational Theory and Mathematics |
Publication ISSN: | 1468-0394 |
Last Modified: | 07 Oct 2024 07:52 |
Date Deposited: | 13 Oct 2023 12:33 |
Full Text Link: | |
Related URLs: |
https://onlinel ... 1111/exsy.13461
(Publisher URL) http://www.scop ... tnerID=8YFLogxK (Scopus URL) |
PURE Output Type: | Article |
Published Date: | 2024-01 |
Published Online Date: | 2023-10-10 |
Accepted Date: | 2023-09-04 |
Authors: |
Lai, Peichao
Ye, Feiyang Fu, Yang-Geng Chen, Zhiwei Wu, Yingjie Wang, Yilei Chang, Victor ( 0000-0002-8012-5852) |