Break it Down into BTS: Basic, Tiniest Subword Units for Korean
Nayeon Kim, Jun-Hyung Park, Joon-Young Choi, Eojin Jeon, Youjin Kang, SangKeun Lee
Abstract
We introduce Basic, Tiniest Subword (BTS) units for the Korean language, which are inspired by the invention principle of Hangeul, the Korean writing system. Instead of relying on 51 Korean consonant and vowel letters, we form the letters from BTS units by adding strokes or combining them. To examine the impact of BTS units on Korean language processing, we develop a novel BTS-based word embedding framework that is readily applicable to various models. Our experiments reveal that BTS units significantly improve the performance of Korean word embedding on all intrinsic and extrinsic tasks in our evaluation. In particular, BTS-based word embedding outperforms the state-of-theart Korean word embedding by 11.8% in word analogy. We further investigate the unique advantages provided by BTS units through indepth analysis.
BibTeX
@inproceedings{kim-etal-2022-break,
title = "Break it Down into {BTS}: Basic, Tiniest Subword Units for {K}orean",
author = "Kim, Nayeon and
Park, Jun-Hyung and
Choi, Joon-Young and
Jeon, Eojin and
Kang, Youjin and
Lee, SangKeun",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.472/",
doi = "10.18653/v1/2022.emnlp-main.472",
pages = "7007--7024"
}