Generating Weather Comments from Meteorological Simulations

Soichiro Murakami, Sora Tanaka, Masatsugu Hangyo, Hidetaka Kamigaito, Kotaro Funakoshi, Hiroya Takamura, Manabu Okumura


Abstract
The task of generating weather-forecast comments from meteorological simulations has the following requirements: (i) the changes in numerical values for various physical quantities need to be considered, (ii) the weather comments should be dependent on delivery time and area information, and (iii) the comments should provide useful information for users. To meet these requirements, we propose a data-to-text model that incorporates three types of encoders for numerical forecast maps, observation data, and meta-data. We also introduce weather labels representing weather information, such as sunny and rain, for our model to explicitly describe useful information. We conducted automatic and human evaluations. The results indicate that our model performed best against baselines in terms of informativeness. We make our code and data publicly available.
Anthology ID:
2021.eacl-main.125
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1462–1473
Language:
URL:
https://aclanthology.org/2021.eacl-main.125
DOI:
10.18653/v1/2021.eacl-main.125
Bibkey:
Cite (ACL):
Soichiro Murakami, Sora Tanaka, Masatsugu Hangyo, Hidetaka Kamigaito, Kotaro Funakoshi, Hiroya Takamura, and Manabu Okumura. 2021. Generating Weather Comments from Meteorological Simulations. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1462–1473, Online. Association for Computational Linguistics.
Cite (Informal):
Generating Weather Comments from Meteorological Simulations (Murakami et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.125.pdf
Code
 titech-nlp/pinpoint-weather