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
摘要
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 BTSbased 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. Our code is available at https: //github.com/irishev/BTS .
问 Lune
尽管问,回答会引用原文。
Lune 会读完全文和相关的 Paper,每个回答都附上所依据的原文段落。
引用它的顶会 Paper2
- CHEF in the Language Kitchen: A Generative Data Augmentation Leveraging Korean Morpheme IngredientsJaehyung Seo, Hyeonseok Moon, Jaewook Lee, Sugyeong Eo 等EMNLP 2023 · 1 次引用
- Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in KoreanSungHo Kim, Nayeon Kim, Taehee Jeon, SangKeun LeeACL 2025
它引用的 Paper1
相关 Paper
- KOMBO: Korean Character Representations Based on the Combination Rules of SubcharactersSungHo Kim, Juhyeong Park, Yeachan Kim, SangKeun LeeACL Findings 2024 · 1 次引用
- SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language ModelsSungHo Kim, Juhyeong Park, Eda Atalay, SangKeun LeeACL Findings 2026
- An Ensemble Distillation Framework for Sentence Embeddings with Multilingual Round-Trip TranslationTianyu Zong, Likun ZhangAAAI 2023 · 1 次引用
- Beyond Distribution: Investigating Language Models' Understanding of Sino-Korean MorphemesTaehee JeonEMNLP Findings 2025
- Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine TranslationJungseob Lee, Hyeonseok Moon, Seungjun Lee, Chanjun Park 等ACL Findings 2024 · 1 次引用
