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 2106.00980cs.AI
收藏

面向通用表单理解的端到端层次关系抽取

End-to-End Hierarchical Relation Extraction for Generic Form Understanding

Cinnamon AI Labs(肉桂人工智能实验室)

Tuan-Anh Nguyen Dang, Duc-Thanh Hoang, Quang-Bach Tran, Chih-Wei Pan, Thanh-Dat Nguyen

摘要:

表单理解是一个具有挑战性的问题,其目的是从输入文档中识别语义实体及其层次关系。以前的方法面临着处理任务的复杂性,因此分别对待这些目标的显着困难。为此,我们提出了一种新型的深度神经网络,以端到端的方式联合执行实体检测和链接预测。我们的模型扩展了多级注意U网的结构,部分强度字段和部分关联字段的链接预测,丰富了空间信息流与实体链接的额外监督。我们证明了该模型的有效性的形式理解在嘈杂的扫描文档(FUNSD)数据集,其中我们的方法大大优于原始模型和国家的最先进的基线在实体标签和实体链接任务。

英文摘要:

Form understanding is a challenging problem which aims to recognize semantic entities from the input document and their hierarchical relations. Previous approaches face significant difficulty dealing with the complexity of the task, thus treat these objectives separately. To this end, we present a novel deep neural network to jointly perform both entity detection and link prediction in an end-to-end fashion. Our model extends the Multi-stage Attentional U-Net architecture with the Part-Intensity Fields and Part-Association Fields for link prediction, enriching the spatial information flow with the additional supervision from entity linking. We demonstrate the effectiveness of the model on the Form Understanding in Noisy Scanned Documents (FUNSD) dataset, where our method substantially outperforms the original model and state-of-the-art baselines in both Entity Labeling and Entity Linking task.

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。

↑