Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry. However, despite significant progress in traditional NER methods, the extraction of Complex Named Entities remains a relatively unexplored area. In this paper, we propose a novel system that combines object detection for Document Layout Analysis (DLA) with weakly supervised learning to address the challenge of extracting discontinuous complex named entities in legal documents. Notably, to the best of our knowledge, this is the first work to apply weak supervision to DLA. Our experimental results show that the model trained solely on pseudo labels outperforms the supervised baseline when gold-standard data is limited, highlighting the effectiveness of our proposed approach in reducing the dependency on annotated data.

翻译：准确识别命名实体（NER）对于工业界各类信息检索任务至关重要。然而，尽管传统NER方法已取得显著进展，复杂命名实体的提取仍是一个相对未充分探索的领域。本文提出一种结合文档布局分析（DLA）的目标检测与弱监督学习的新颖系统，旨在解决法律文档中不连续复杂命名实体的提取难题。值得注意的是，据我们所知，这是首个将弱监督学习应用于DLA的研究工作。实验结果表明，在黄金标准数据有限的情况下，仅基于伪标签训练的模型表现优于有监督基线方法，这充分证明了我们提出的方法在降低对标注数据依赖性方面的有效性。