Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification

Heng Gong, Wei Bi, Xiaocheng Feng, Bing Qin, Xiaojiang Liu, Ting Liu


Abstract
Neural table-to-text models, which select and order salient data, as well as verbalizing them fluently via surface realization, have achieved promising progress. Based on results from previous work, the performance bottleneck of current models lies in the stage of content planing (selecting and ordering salient content from the input). That is, performance drops drastically when an oracle content plan is replaced by a model-inferred one during surface realization. In this paper, we propose to enhance neural content planning by (1) understanding data values with contextual numerical value representations that bring the sense of value comparison into content planning; (2) verifying the importance and ordering of the selected sequence of records with policy gradient. We evaluated our model on ROTOWIRE and MLB, two datasets on this task, and results show that our model outperforms existing systems with respect to content planning metrics.
Anthology ID:
2020.findings-emnlp.262
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2905–2914
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.262
DOI:
10.18653/v1/2020.findings-emnlp.262
Bibkey:
Cite (ACL):
Heng Gong, Wei Bi, Xiaocheng Feng, Bing Qin, Xiaojiang Liu, and Ting Liu. 2020. Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2905–2914, Online. Association for Computational Linguistics.
Cite (Informal):
Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification (Gong et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.262.pdf
Optional supplementary material:
 2020.findings-emnlp.262.OptionalSupplementaryMaterial.zip
Data
RotoWire