An Integrated Search System for Korea Weather Data

Jinkyung Jo, Dayeon Ki, Soyoung Yoon, Minjoon Seo


Abstract
We introduce WeatherSearch, an integrated search system deployed at the Korea Meteorological Administration (KMA). WeatherSearch enables users to retrieve all the relevant data for weather forecasting from a massive weather database with simple natural language queries. We carefully design and conduct multiple expert surveys and interviews for template creation and apply data augmentation techniques including template filling to collect 4 million data points with minimal human labors. We then finetune mT5 on the collected dataset and achieve an average MRR of 0.66 and an average Recall of 0.82. We also discuss weather-data-specific characteristics that should be taken into account for creating such a system. We hope our paper serves as a simple and effective guideline for those designing similar systems in other regions of the world.
Anthology ID:
2023.emnlp-industry.71
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2023
Address:
Singapore
Editors:
Mingxuan Wang, Imed Zitouni
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
765–774
Language:
URL:
https://aclanthology.org/2023.emnlp-industry.71
DOI:
10.18653/v1/2023.emnlp-industry.71
Bibkey:
Cite (ACL):
Jinkyung Jo, Dayeon Ki, Soyoung Yoon, and Minjoon Seo. 2023. An Integrated Search System for Korea Weather Data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 765–774, Singapore. Association for Computational Linguistics.
Cite (Informal):
An Integrated Search System for Korea Weather Data (Jo et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-industry.71.pdf
Video:
 https://aclanthology.org/2023.emnlp-industry.71.mp4