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
- 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/W19-8622.pdf