arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.05613cs.CLcs.AI
收藏

对比训练改进半结构化文档的Zero-Shot分类

Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents

University of Michigan(密歇根大学);AWS AI Labs(亚马逊云科技人工智能实验室)

Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros

摘要:

我们研究了半结构化文档分类在一个zero-shot设置。半结构化文档的分类比标准的非结构化文档更具挑战性,因为位置、布局和样式信息在解释此类文档时起着至关重要的作用。在训练和测试期间类别都是固定的标准分类设置在可能出现新文档类别的动态环境中是不够的。我们专注于专门的zero-shot设置,其中的推理是在新的看不见的类。为了解决这个问题,我们提出了一种基于匹配的方法,它依赖于一个成对的对比目标进行预训练和微调。我们的研究结果表明,在监督和无监督zero-shot设置中,Macro F $_1$从建议的预训练步骤中得到了显着的提升。

英文摘要:

We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured documents, as positional, layout, and style information play a vital role in interpreting such documents. The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge. We focus exclusively on the zero-shot setting where inference is done on new unseen classes. To address this task, we propose a matching-based approach that relies on a pairwise contrastive objective for both pretraining and fine-tuning. Our results show a significant boost in Macro F$_1$ from the proposed pretraining step in both supervised and unsupervised zero-shot settings.

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。

↑