Hugging Face Daily Papers · · 3 min read

GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

👏</p>\n","updatedAt":"2026-05-13T06:14:56.536Z","author":{"_id":"5e6a3d4ea9afd5125d9ec064","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1584020801691-noauth.jpeg","fullname":"Stefan Schweter","name":"stefan-it","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3898,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"vi","probability":0.12120208144187927},"editors":["stefan-it"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1584020801691-noauth.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.10108","authors":[{"_id":"6a0416cd86b054ce2fa40fc3","name":"Ihor Stepanov","hidden":false},{"_id":"6a0416cd86b054ce2fa40fc4","name":"Oleksandr Lukashov","hidden":false},{"_id":"6a0416cd86b054ce2fa40fc5","name":"Mykhailo Shtopko","hidden":false},{"_id":"6a0416cd86b054ce2fa40fc6","name":"Vivek Kalyanarangan","hidden":false}],"publishedAt":"2026-05-11T00:00:00.000Z","submittedOnDailyAt":"2026-05-13T00:00:00.000Z","title":"GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction","submittedOnDailyBy":{"_id":"5e6a3d4ea9afd5125d9ec064","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1584020801691-noauth.jpeg","isPro":true,"fullname":"Stefan Schweter","user":"stefan-it","type":"user","name":"stefan-it"},"summary":"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.","upvotes":1,"discussionId":"6a0416ce86b054ce2fa40fc7","ai_summary":"A unified model for joint named entity recognition and relation extraction that uses a shared transformer encoder to simultaneously identify entities and extract relations with zero-shot capabilities.","ai_keywords":["joint named entity recognition","relation extraction","GLiNER","bidirectional transformer encoder","zero-shot extraction","entity pair representations","relation scoring module","CoNLL04","DocRED","FewRel","CrossRE"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"5e6a3d4ea9afd5125d9ec064","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1584020801691-noauth.jpeg","isPro":true,"fullname":"Stefan Schweter","user":"stefan-it","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.10108.md"}">
Papers
arxiv:2605.10108

GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction

Published on May 11
· Submitted by
Stefan Schweter
on May 13
Authors:
,
,
,

Abstract

A unified model for joint named entity recognition and relation extraction that uses a shared transformer encoder to simultaneously identify entities and extract relations with zero-shot capabilities.

AI-generated summary

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.

Community

Paper submitter about 15 hours ago

👏

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.10108
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.10108 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.10108 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.10108 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers