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 2307.02882cs.CLcs.AI
收藏

对比即所需

Contrast Is All You Need

Utrecht University(乌得勒支大学);Shareforce B.V.;Tilburg University(蒂尔堡大学)

Burak Kilic, Florix Bex, Albert Gatt

AI总结:

针对标注数据少且不平衡的法律分类场景,本文提出使用SetFit对比学习方法,相比普通微调能在更少样本下取得更好效果,且基于LIME分析表明对比学习使模型更自信地依赖具法律信息量的特征进行决策。

摘要:

在本研究中,我们分析了数据稀缺的分类场景,其中可用的标注法律数据量少且不平衡,可能会损害结果质量。我们重点关注了两个微调目标:SetFit(Sentence Transformer Finetuning,一种对比学习设置)以及在法律条款分类任务上的普通微调设置。此外,我们比较了用 LIME(Local Interpretable Model-agnostic Explanations)提取的特征,以查看哪些特定特征促成了模型的分类决策。结果表明,使用 SetFit 的对比设置在使用一小部分训练样本的情况下,表现优于普通微调。LIME 结果显示,对比学习方法有助于增强具有法律信息量并有助于分类结果的正向和负向特征。因此,用对比目标微调的模型似乎能更自信地基于具有法律信息量的特征做出决策。

英文摘要:

In this study, we analyze data-scarce classification scenarios, where available labeled legal data is small and imbalanced, potentially hurting the quality of the results. We focused on two finetuning objectives; SetFit (Sentence Transformer Finetuning), a contrastive learning setup, and a vanilla finetuning setup on a legal provision classification task. Additionally, we compare the features that are extracted with LIME (Local Interpretable Model-agnostic Explanations) to see which particular features contributed to the model's classification decisions. The results show that a contrastive setup with SetFit performed better than vanilla finetuning while using a fraction of the training samples. LIME results show that the contrastive learning approach helps boost both positive and negative features which are legally informative and contribute to the classification results. Thus a model finetuned with a contrastive objective seems to base its decisions more confidently on legally informative features.

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。

↑