Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation

Liang Li, Can Ma, Yinliang Yue, Dayong Hu


Abstract
Table-to-text generation aims at automatically generating natural text to help people conveniently obtain salient information in tables. Although neural models for table-to-text have achieved remarkable progress, some problems are still overlooked. Previous methods cannot deduce the factual results from the entity’s (player or team) performance and the relations between entities. To solve this issue, we first build an entity graph from the input tables and introduce a reasoning module to perform reasoning on the graph. Moreover, there are different relations (e.g., the numeric size relation and the importance relation) between records in different dimensions. And these relations may contribute to the data-to-text generation. However, it is hard for a vanilla encoder to capture these. Consequently, we propose to utilize two auxiliary tasks, Number Ranking (NR) and Importance Ranking (IR), to supervise the encoder to capture the different relations. Experimental results on ROTOWIRE and RW-FG show that our method not only has a good generalization but also outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering.
Anthology ID:
2021.acl-long.466
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5979–5989
Language:
URL:
https://aclanthology.org/2021.acl-long.466
DOI:
10.18653/v1/2021.acl-long.466
Bibkey:
Cite (ACL):
Liang Li, Can Ma, Yinliang Yue, and Dayong Hu. 2021. Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5979–5989, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation (Li et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.466.pdf
Video:
 https://aclanthology.org/2021.acl-long.466.mp4
Code
 liang8qi/data2textwithauxiliarysupervision
Data
RotoWire