@inproceedings{jo-etal-2023-integrated,
title = "An Integrated Search System for {K}orea Weather Data",
author = "Jo, Jinkyung and
Ki, Dayeon and
Yoon, Soyoung and
Seo, Minjoon",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.71",
doi = "10.18653/v1/2023.emnlp-industry.71",
pages = "765--774",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jo-etal-2023-integrated">
<titleInfo>
<title>An Integrated Search System for Korea Weather Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinkyung</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayeon</namePart>
<namePart type="family">Ki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soyoung</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">jo-etal-2023-integrated</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.71</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.71</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>765</start>
<end>774</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Integrated Search System for Korea Weather Data
%A Jo, Jinkyung
%A Ki, Dayeon
%A Yoon, Soyoung
%A Seo, Minjoon
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F jo-etal-2023-integrated
%X 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.
%R 10.18653/v1/2023.emnlp-industry.71
%U https://aclanthology.org/2023.emnlp-industry.71
%U https://doi.org/10.18653/v1/2023.emnlp-industry.71
%P 765-774
Markdown (Informal)
[An Integrated Search System for Korea Weather Data](https://aclanthology.org/2023.emnlp-industry.71) (Jo et al., EMNLP 2023)
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.