ACL

Guidance-Based Prompt Data Augmentation in Specialized Domains for Named Entity Recognition

基于指导的提示数据增强在专业领域中的命名实体识别

Hyeonseok Kang, Hyein Seo, Jeesu Jung, Sangkeun Jung, Du-Seong Chang, Riwoo Chung

机构 * Computer Science and Engineering, Chungnam National University, Republic of Korea（Chungnam 国立大学计算机科学与工程系） ； KT Corporation, Republic of Korea（KT 公司） 纠错

AI总结 本研究提出一种基于指导的提示数据增强方法，通过抽象上下文和句子结构生成多样化句子，提升专业领域命名实体识别任务的训练性能。

Journal ref Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024

LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models

LEANCODE: 为预训练大语言模型的代码简化更好地理解模型

Yan Wang, Ling Ding, Tien N Nguyen, Shaohua Wang, Yanan Zheng

AI总结 LeanCode通过上下文感知注意力分数优化代码简化，提升预训练大语言模型在代码搜索和摘要任务中的性能。

Comments ACL 2025 Main. Our code and dataset are available at https://github.com/akai-sh/LeanCode

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1551-1567 (2025)