Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions

Yerin Hwang, Yongil Kim, Hyunkyung Bae, Jeesoo Bang, Hwanhee Lee, Kyomin Jung


Abstract
Existing English-based text similarity measurements primarily focus on the semantic dimension, neglecting the unique linguistic attributes found in languages like Korean, where honorific expressions are explicitly integrated. To address this limitation, this study proposes Kosmic, a novel Korean text-similarity metric that encompasses the semantic and tonal facets of a given text pair. For the evaluation, we introduce a novel benchmark annotated by human experts, empirically showing that Kosmic outperforms the existing method. Moreover, by leveraging Kosmic, we assess various Korean paraphrasing methods to determine which techniques are most effective in preserving semantics and tone.
Anthology ID:
2024.lrec-main.870
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
9954–9960
Language:
URL:
https://aclanthology.org/2024.lrec-main.870
DOI:
Bibkey:
Cite (ACL):
Yerin Hwang, Yongil Kim, Hyunkyung Bae, Jeesoo Bang, Hwanhee Lee, and Kyomin Jung. 2024. Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9954–9960, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions (Hwang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.870.pdf