GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction
2026-05-11 • Computation and Language
Computation and LanguageMachine Learning
AI summaryⓘ
The authors present GLiNER-Relex, a single model that can find names of things (entities) and how they are connected (relations) in text all at once. Their approach uses one shared transformer system to understand text, entity types, and relation types together, even for new types it hasn't seen before. They tested it on several standard datasets and found it works well compared to other specialized models and large language models, while being efficient. The authors also released the model and code openly, making it easy to extract entities and relations with custom labels in one step.
named entity recognitionrelation extractiontransformer encoderzero-shot learningknowledge graphsentity pair representationrelation scoringCoNLL04DocREDFewRel
Authors
Ihor Stepanov, Oleksandr Lukashov, Mykhailo Shtopko, Vivek Kalyanarangan
Abstract
Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs from unstructured text. While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduce GLiNER-Relex, a unified architecture that extends the GLiNER framework to perform both entity recognition and relation extraction in a single model. Our approach leverages a shared bidirectional transformer encoder to jointly represent text, entity type labels, and relation type labels, enabling zero-shot extraction of arbitrary entity and relation types specified at inference time. GLiNER-Relex constructs entity pair representations from recognized spans and scores them against relation type embeddings using a dedicated relation scoring module. We evaluate our model on four standard relation extraction benchmarks: CoNLL04, DocRED, FewRel, and CrossRE, and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the computational efficiency characteristic of the GLiNER family. The model is released as an open-source Python package with a simple inference API that allows users to specify arbitrary entity and relation type labels at inference time and obtain both entities and relation triplets in a single call. All models and code are publicly available.