arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.02739cs.CLcs.AIcs.LG
收藏

TARDiS:用于提升多样性与可分离性的文本增强

TARDiS : Text Augmentation for Refining Diversity and Separability

School of Computer Science and Engineering, Korea University of Technology and Education (KOREATECH)(韩国技术教育大学计算机科学与工程学院(KOREATECH))

Kyungmin Kim, SangHun Im, GiBaeg Kim, Heung-Seon Oh

AI总结:

针对少样本文本分类,本文提出基于 LLM 的两阶段文本增强方法 TARDiS,通过 SEG、CEG 生成流程和类别适应机制提升样本多样性、可分离性与类别一致性,并在多项任务中超过现有方法。

摘要:

文本增强(TA)是文本分类中的一项关键技术,尤其是在少样本场景下。本文提出一种新颖的基于 LLM 的 TA 方法 TARDiS,以应对两阶段 TA 方法在生成与对齐阶段固有的挑战。在生成阶段,我们提出 SEG 和 CEG 两种生成流程,结合多个类别特定提示来增强多样性与可分离性。在对齐阶段,我们引入类别适应(CA)方法,通过验证和修改确保生成样本与其目标类别对齐。实验结果表明 TARDiS 具有有效性,在多种少样本文本分类任务中优于最先进的基于 LLM 的 TA 方法。深入分析证实了各阶段的具体行为。

英文摘要:

Text augmentation (TA) is a critical technique for text classification, especially in few-shot settings. This paper introduces a novel LLM-based TA method, TARDiS, to address challenges inherent in the generation and alignment stages of two-stage TA methods. For the generation stage, we propose two generation processes, SEG and CEG, incorporating multiple class-specific prompts to enhance diversity and separability. For the alignment stage, we introduce a class adaptation (CA) method to ensure that generated examples align with their target classes through verification and modification. Experimental results demonstrate TARDiS's effectiveness, outperforming state-of-the-art LLM-based TA methods in various few-shot text classification tasks. An in-depth analysis confirms the detailed behaviors at each stage.

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。

↑