Plan-then-Generate: Controlled Data-to-Text Generation via Planning
View / Open Files
Publication Date
2021-01-01Journal Title
Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
ISBN
9781955917100
Pages
895-909
Type
Conference Object
This Version
VoR
Metadata
Show full item recordCitation
Su, Y., Vandyke, D., Wang, S., Fang, Y., & Collier, N. (2021). Plan-then-Generate: Controlled Data-to-Text Generation via Planning. Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021, 895-909. https://doi.org/10.17863/CAM.84984
Abstract
Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, we propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-totext models. Extensive experiments and analyses are conducted on two benchmark datasets, ToTTo and WebNLG. The results show that our model is able to control both the intrasentence and inter-sentence structure of the generated output. Furthermore, empirical comparisons against previous state-of-the-art methods show that our model improves the generation quality as well as the output diversity as judged by human and automatic evaluations.
Embargo Lift Date
2100-01-01
Identifiers
External DOI: https://doi.org/10.17863/CAM.84984
This record's URL: https://www.repository.cam.ac.uk/handle/1810/337575
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.