基于韩文字母组合规则，构建更符合语言本质的字符表示方法
KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters
- 利用韩文音素组合规律构建字符表征
- 在5项任务上平均提升2.11%性能
- 适合需要精准解析韩语结构的研究场景
韩文（Hangeul）的字符表示严格遵循1446年《训民正音》中记载的造字原则。然而，现有韩语预训练模型忽略了这些语言学特性。本文提出KOMBO框架，首次将韩文造字原理融入字符表征。实验表明，该方法在五项韩语自然语言理解任务中，平均优于当前最优韩语模型2.11%。大量实验证明，该方法能有效捕捉韩语的语言特征，揭示了基于子字符的表征方式相较于传统子词方法的优势。代码已公开于https://github.com/SungHo3268/KOMBO。
原文摘要 · Abstract (English)
The Korean writing system, \textit{Hangeul}, has a unique character representation rigidly following the invention principles recorded in \textit{Hunminjeongeum}.\footnote{\textit{Hunminjeongeum} is a book published in 1446 that describes the principles of invention and usage of \textit{Hangeul}, devised by King Sejong \cite{Hunminjeongeum_Guide}.} However, existing pre-trained language models (PLMs) for Korean have overlooked these principles. In this paper, we introduce a novel framework for Korean PLMs called KOMBO, which firstly brings the invention principles of \textit{Hangeul} to represent character. Our proposed method, KOMBO, exhibits notable experimental proficiency across diverse NLP tasks. In particular, our method outperforms the state-of-the-art Korean PLM by an average of 2.11\% in five Korean natural language understanding tasks. Furthermore, extensive experiments demonstrate that our proposed method is suitable for comprehending the linguistic features of the Korean language. Consequently, we shed light on the superiority of using subcharacters over the typical subword-based approach for Korean PLMs. Our code is available at: [https://github.com/SungHo3268/KOMBO](https://github.com/SungHo3268/KOMBO).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。