面向低资源事件抽取的定向增强方法
Targeted Augmentation for Low-Resource Event Extraction
AI总结：
针对低资源事件抽取中现有数据增强难以平衡强弱增强效果的问题，提出结合定向增强与反向验证的新范式，生成更优质的增强样本，实验验证了其有效性并指明了未来改进方向。
摘要：
低资源信息抽取因有限训练样本固有的信息稀缺性，其挑战的应对仍是一项待解决的持续问题。现有被视作潜在解决方案的数据增强方法，难以在弱增强（如同义词增强）与强增强（如缺乏合理引导的条件生成）之间取得平衡。本文提出一种新范式，采用定向增强与反向验证，生成具备更高多样性、极性合理性、准确性与连贯性的增强样本。大量实验结果验证了所提范式的有效性。此外，本文还讨论了已发现的局限性，为未来的改进方向提供了思路。
英文摘要：
Addressing the challenge of low-resource information extraction remains an ongoing issue due to the inherent information scarcity within limited training examples. Existing data augmentation methods, considered potential solutions, struggle to strike a balance between weak augmentation (e.g., synonym augmentation) and drastic augmentation (e.g., conditional generation without proper guidance). This paper introduces a novel paradigm that employs targeted augmentation and back validation to produce augmented examples with enhanced diversity, polarity, accuracy, and coherence. Extensive experimental results demonstrate the effectiveness of the proposed paradigm. Furthermore, identified limitations are discussed, shedding light on areas for future improvement.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
