A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG

Guanyi Chen, Jin-Ge Yao


Abstract
Automatic natural language generation systems need to use the contextually-appropriate verbs when describing different kinds of facts or events, which has triggered research interest on verb selection for data-to-text generation. In this paper, we discuss a few limitations of the current task settings and the evaluation metrics. We also provide two simple, efficient, interpretable baseline approaches for statistical selection of trend verbs, which give a strong performance on both previously used evaluation metrics and our new evaluation.
Anthology ID:
W19-8622
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Editors:
Kees van Deemter, Chenghua Lin, Hiroya Takamura
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
158–163
Language:
URL:
https://aclanthology.org/W19-8622
DOI:
10.18653/v1/W19-8622
Bibkey:
Cite (ACL):
Guanyi Chen and Jin-Ge Yao. 2019. A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG. In Proceedings of the 12th International Conference on Natural Language Generation, pages 158–163, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG (Chen & Yao, INLG 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/W19-8622.pdf
Supplementary attachment:
 W19-8622.Supplementary_Attachment.pdf