Named entity recognition is a traditional task in natural language processing. In particular, nested entity recognition receives extensive attention for the widespread existence of the nesting scenario. The latest research migrates the well-established paradigm of set prediction in object detection to cope with entity nesting. However, the manual creation of query vectors, which fail to adapt to the rich semantic information in the context, limits these approaches. An end-to-end entity detection approach with proposer and regressor is presented in this paper to tackle the issues. First, the proposer utilizes the feature pyramid network to generate high-quality entity proposals. Then, the regressor refines the proposals for generating the final prediction. The model adopts encoder-only architecture and thus obtains the advantages of the richness of query semantics, high precision of entity localization, and easiness for model training. Moreover, we introduce the novel spatially modulated attention and progressive refinement for further improvement. Extensive experiments demonstrate that our model achieves advanced performance in flat and nested NER, achieving a new state-of-the-art F1 score of 80.74 on the GENIA dataset and 72.38 on the WeiboNER dataset.
翻译:命名实体的识别是自然语言处理中的一项传统任务。特别是,嵌套实体的识别受到广泛关注,因为巢式设想方案的广泛存在。最新的研究转移了在物体检测方面既定的设定预测模式,以适应实体的嵌套。然而,人工创建查询矢量,无法适应丰富的语义信息,限制了这些方法。本文提出了由提议者和递后者组成的端对端实体的检测方法,以解决这些问题。首先,提议者利用地貌金字塔网络生成高质量的实体提案。然后,回归者完善了最终预测的建议。模型采用了只使用编码器的模型,从而获得了查询语义丰富、实体定位高度精确和模型培训容易的优势。此外,我们引入了新的空间调节式关注和逐步完善,以进一步加以改进。广泛的实验表明,我们的模型在固定和嵌入式的NER网络中取得了先进的性能,从而在GENIA数据设置和我们GENA数据设置的80.74分级中实现了新的状态F1分数。