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

TL;DR

This paper presents GLiNER-bi-Encoder, a scalable architecture for NER that efficiently recognizes millions of entity types with state-of-the-art zero-shot performance and significantly improved throughput.

Contribution

It introduces a bi-encoder design for NER that overcomes quadratic complexity, enabling industrial-scale recognition of vast label sets with minimal overhead.

Findings

Achieves 61.5% Micro-F1 on CrossNER benchmark.

Up to 130x throughput improvement with pre-computed label embeddings.

Enables high-performance entity linking with GLiNKER framework.

Abstract

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.