arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.18487cs.CLcs.LG
收藏

百万标签命名实体识别:通过GLiNER双编码器打破规模限制

The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder

Knowledgator Engineering(Knowledgator工程)

Ihor Stepanov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov

AI总结:

GLiNER-bi-Encoder通过双编码器架构实现百万级标签的命名实体识别,提升零样本性能和处理效率,同时支持大规模知识库的实体链接。

摘要:

本文介绍了GLiNER-bi-Encoder,一种新颖的命名实体识别(NER)架构,该架构在零样本灵活性与工业级效率之间取得了平衡。尽管原始GLiNER框架具有强大的泛化能力,但其联合编码方法在实体标签数量增加时会面临二次复杂度的问题。我们提出的双编码器设计将过程拆分为专门的标签编码器和上下文编码器,有效消除了上下文窗口瓶颈。该架构使同时识别数千甚至数百万种实体类型成为可能,且开销极低。实验结果表明,该方法在零样本性能上达到最先进的水平,在CrossNER基准测试中实现了61.5%的Micro-F1。关键在于通过预计算的标签嵌入,GLiNER-bi-Encoder在1024个标签的情况下,相比其单编码器前代方法,吞吐量提升了高达130倍。此外,我们还引入了GLiNKER,一个模块化框架,利用该架构在大规模知识库如Wikidata上实现高性能的实体链接。

英文摘要:

This paper introduces GLiNER-bi-Encoder, a novel architecture for Named Entity Recognition (NER) that harmonizes zero-shot flexibility with industrial-scale efficiency. While the original GLiNER framework offers strong generalization, its joint-encoding approach suffers from quadratic complexity as the number of entity labels increases. Our proposed bi-encoder design decouples the process into a dedicated label encoder and a context encoder, effectively removing the context-window bottleneck. This architecture enables the simultaneous recognition of thousands, and potentially millions, of entity types with minimal overhead. Experimental results demonstrate state-of-the-art zero-shot performance, achieving 61.5 percent Micro-F1 on the CrossNER benchmark. Crucially, by leveraging pre-computed label embeddings, GLiNER-bi-Encoder achieves up to a 130 times throughput improvement at 1024 labels compared to its uni-encoder predecessors. Furthermore, we introduce GLiNKER, a modular framework that leverages this architecture for high-performance entity linking across massive knowledge bases such as Wikidata.

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。

↑