Information Extraction (IE) focuses on transforming unstructured data into structured knowledge, of which Named Entity Recognition (NER) is a fundamental component. In the realm of Information Retrieval (IR), effectively recognizing entities can substantially enhance the precision of search and recommendation systems. Existing methods frame NER as a sequence labeling task, which requires extra data and, therefore may be limited in terms of sustainability. One promising solution is to employ a Machine Reading Comprehension (MRC) approach for NER tasks, thereby eliminating the dependence on additional data. This process encounters key challenges, including: 1) Unconventional predictions; 2) Inefficient multi-stream processing; 3) Absence of a proficient reasoning strategy. To this end, we present the Single-Stream Reasoner (SSR), a solution utilizing a reasoning strategy and standardized inputs. This yields a type-agnostic solution for both flat and nested NER tasks, without the need for additional data. On ten NER benchmarks, SSR achieved state-of-the-art results, highlighting its robustness. Furthermore, we illustrated its efficiency through convergence, inference speed, and low-resource scenario performance comparisons. Our architecture displays adaptability and can effortlessly merge with various foundational models and reasoning strategies, fostering advancements in both IR and IE fields.

信息提取（IE）专注于将非结构化数据转换为结构化知识，命名实体识别（NER）是其中的基本组成部分。在信息检索（IR）领域，有效识别实体可以大大提高搜索和推荐系统的精度。现有方法将 NER 构建为序列标记任务，这需要额外的数据，因此在可持续性方面可能受到限制。一种有前景的解决方案是对 NER 任务采用机器阅读理解 (MRC) 方法，从而消除对额外数据的依赖。这个过程遇到了关键挑战，包括：1）非常规预测； 2）多流处理效率低下； 3）缺乏熟练的推理策略。为此，我们提出了单流推理器（SSR），这是一种利用推理策略和标准化输入的解决方案。这为平面和嵌套 NER 任务提供了一个与类型无关的解决方案，而不需要额外的数据。在十项 NER 基准测试中，SSR 取得了最先进的结果，凸显了其稳健性。此外，我们通过收敛、推理速度和低资源场景性能比较来说明其效率。我们的架构表现出适应性，可以轻松地与各种基础模型和推理策略融合，促进 IR 和 IE 领域的进步。