KOAS: Korean Text Offensiveness Analysis System

San Hee Park; Kang Min Kim; Seonhee Cho; Jun Hyung Park; Hyuntae Park; Hyuna Kim; Seongwon Chung; Sang Keun Lee

KOAS: Korean Text Offensiveness Analysis System

San Hee Park, Kang Min Kim, Seonhee Cho, Jun Hyung Park, Hyuntae Park, Hyuna Kim, Seongwon Chung, Sang Keun Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Warning: This manuscript contains a certain level of offensive expression. As communication through social media platforms has grown immensely, the increasing prevalence of offensive language online has become a critical problem. Notably in Korea, one of the countries with the highest Internet usage, automatic detection of offensive expressions has recently been brought to attention. However, morphological richness and complex syntax of Korean causes difficulties in neural model training. Furthermore, most of previous studies mainly focus on the detection of abusive language, disregarding implicit offensiveness and underestimating a different degree of intensity. To tackle these problems, we present KOAS, a system that fully exploits both contextual and linguistic features and estimates an offensiveness score for a text. We carefully designed KOAS with a multi-task learning framework and constructed a Korean dataset for offensive analysis from various domains. Refer for a detailed demonstration.

Original language	English
Title of host publication	EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing
Subtitle of host publication	System Demonstrations
Publisher	Association for Computational Linguistics (ACL)
Pages	72-78
Number of pages	7
ISBN (Electronic)	9781955917117
Publication status	Published - 2021
Event	2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 - Virtual, Punta Cana, Dominican Republic Duration: 2021 Nov 7 → 2021 Nov 11

Publication series

Name	EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Conference

Conference	2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Country/Territory	Dominican Republic
City	Virtual, Punta Cana
Period	21/11/7 → 21/11/11

Bibliographical note

Funding Information:
We thank the anonymous reviewers for their helpful comments. This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2021R1A2C3010430) and the Basic Research Program through the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1A4A1018309).

Publisher Copyright:
© 2021 Association for Computational Linguistics.

ASJC Scopus subject areas

Computer Science Applications
Computational Theory and Mathematics
Information Systems

Cite this

Park, S. H., Kim, K. M., Cho, S., Park, J. H., Park, H., Kim, H., Chung, S., & Lee, S. K. (2021). KOAS: Korean Text Offensiveness Analysis System. In EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (pp. 72-78). (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations). Association for Computational Linguistics (ACL).

KOAS: Korean Text Offensiveness Analysis System. / Park, San Hee; Kim, Kang Min; Cho, Seonhee et al.
EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics (ACL), 2021. p. 72-78 (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Park, SH, Kim, KM, Cho, S, Park, JH, Park, H, Kim, H, Chung, S & Lee, SK 2021, KOAS: Korean Text Offensiveness Analysis System. in EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Association for Computational Linguistics (ACL), pp. 72-78, 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual, Punta Cana, Dominican Republic, 21/11/7.

Park SH, Kim KM, Cho S, Park JH, Park H, Kim H et al. KOAS: Korean Text Offensiveness Analysis System. In EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics (ACL). 2021. p. 72-78. (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations).

Park, San Hee ; Kim, Kang Min ; Cho, Seonhee et al. / KOAS : Korean Text Offensiveness Analysis System. EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics (ACL), 2021. pp. 72-78 (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations).

@inproceedings{6616829aa60f4735b345d7ceb71de166,

title = "KOAS: Korean Text Offensiveness Analysis System",

abstract = "Warning: This manuscript contains a certain level of offensive expression. As communication through social media platforms has grown immensely, the increasing prevalence of offensive language online has become a critical problem. Notably in Korea, one of the countries with the highest Internet usage, automatic detection of offensive expressions has recently been brought to attention. However, morphological richness and complex syntax of Korean causes difficulties in neural model training. Furthermore, most of previous studies mainly focus on the detection of abusive language, disregarding implicit offensiveness and underestimating a different degree of intensity. To tackle these problems, we present KOAS, a system that fully exploits both contextual and linguistic features and estimates an offensiveness score for a text. We carefully designed KOAS with a multi-task learning framework and constructed a Korean dataset for offensive analysis from various domains. Refer for a detailed demonstration.",

author = "Park, {San Hee} and Kim, {Kang Min} and Seonhee Cho and Park, {Jun Hyung} and Hyuntae Park and Hyuna Kim and Seongwon Chung and Lee, {Sang Keun}",

note = "Funding Information: We thank the anonymous reviewers for their helpful comments. This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2021R1A2C3010430) and the Basic Research Program through the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1A4A1018309). Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 ; Conference date: 07-11-2021 Through 11-11-2021",

year = "2021",

language = "English",

series = "EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",

publisher = "Association for Computational Linguistics (ACL)",

pages = "72--78",

booktitle = "EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing",

}

TY - GEN

T1 - KOAS

T2 - 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021

AU - Park, San Hee

AU - Kim, Kang Min

AU - Cho, Seonhee

AU - Park, Jun Hyung

AU - Park, Hyuntae

AU - Kim, Hyuna

AU - Chung, Seongwon

AU - Lee, Sang Keun

N1 - Funding Information: We thank the anonymous reviewers for their helpful comments. This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2021R1A2C3010430) and the Basic Research Program through the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1A4A1018309). Publisher Copyright: © 2021 Association for Computational Linguistics.

PY - 2021

Y1 - 2021

N2 - Warning: This manuscript contains a certain level of offensive expression. As communication through social media platforms has grown immensely, the increasing prevalence of offensive language online has become a critical problem. Notably in Korea, one of the countries with the highest Internet usage, automatic detection of offensive expressions has recently been brought to attention. However, morphological richness and complex syntax of Korean causes difficulties in neural model training. Furthermore, most of previous studies mainly focus on the detection of abusive language, disregarding implicit offensiveness and underestimating a different degree of intensity. To tackle these problems, we present KOAS, a system that fully exploits both contextual and linguistic features and estimates an offensiveness score for a text. We carefully designed KOAS with a multi-task learning framework and constructed a Korean dataset for offensive analysis from various domains. Refer for a detailed demonstration.

AB - Warning: This manuscript contains a certain level of offensive expression. As communication through social media platforms has grown immensely, the increasing prevalence of offensive language online has become a critical problem. Notably in Korea, one of the countries with the highest Internet usage, automatic detection of offensive expressions has recently been brought to attention. However, morphological richness and complex syntax of Korean causes difficulties in neural model training. Furthermore, most of previous studies mainly focus on the detection of abusive language, disregarding implicit offensiveness and underestimating a different degree of intensity. To tackle these problems, we present KOAS, a system that fully exploits both contextual and linguistic features and estimates an offensiveness score for a text. We carefully designed KOAS with a multi-task learning framework and constructed a Korean dataset for offensive analysis from various domains. Refer for a detailed demonstration.

UR - http://www.scopus.com/inward/record.url?scp=85127233386&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85127233386

T3 - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

SP - 72

EP - 78

BT - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics (ACL)

Y2 - 7 November 2021 through 11 November 2021

ER -

KOAS: Korean Text Offensiveness Analysis System

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this