KGR4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation
DOI:
https://doi.org/10.1609/aaai.v36i10.21351Keywords:
Speech & Natural Language Processing (SNLP)Abstract
Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are often implausible and grammatically incorrect. In this paper, inspired by the process of humans creating sentences, we propose a novel Knowledge-enhanced Commonsense Generation framework, termed KGR4, consisting of four stages: Retrieval, Retrospect, Refine, Rethink. Under this framework, we first perform retrieval to search for relevant sentences from external corpus as the prototypes. Then, we train the generator that either edits or copies these prototypes to generate candidate sentences, of which potential errors will be fixed by an autoencoder-based refiner. Finally, we select the output sentence from candidate sentences produced by generators with different hyper-parameters. Experimental results and in-depth analysis on the CommonGen benchmark strongly demonstrate the effectiveness of our framework. Particularly, KGR4 obtains 33.56 SPICE in the official leaderboard, outperforming the previously-reported best result by 2.49 SPICE and achieving state-of-the-art performance. We release the code at https://github.com/DeepLearnXMU/KGR-4.Downloads
Published
2022-06-28
How to Cite
Liu, X., Liu, D., Yang, B., Zhang, H., Ding, J., Yao, W., Luo, W., Zhang, H., & Su, J. (2022). KGR4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11029-11037. https://doi.org/10.1609/aaai.v36i10.21351
Issue
Section
AAAI Technical Track on Speech and Natural Language Processing