GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915408374661120 |
|---|---|
| author | Zaratiana, Urchade Pasternak, Gil Boyd, Oliver Hurn-Maloney, George Lewis, Ash |
| author_facet | Zaratiana, Urchade Pasternak, Gil Boyd, Oliver Hurn-Maloney, George Lewis, Ash |
| contents | Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. Built pretrained transformer encoder architecture, GLiNER2 maintains CPU efficiency and compact size while introducing multi-task composition through an intuitive schema-based interface. Our experiments demonstrate competitive performance across extraction and classification tasks with substantial improvements in deployment accessibility compared to LLM-based alternatives. We release GLiNER2 as an open-source pip-installable library with pre-trained models and documentation at https://github.com/fastino-ai/GLiNER2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18546 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface Zaratiana, Urchade Pasternak, Gil Boyd, Oliver Hurn-Maloney, George Lewis, Ash Computation and Language Artificial Intelligence Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. Built pretrained transformer encoder architecture, GLiNER2 maintains CPU efficiency and compact size while introducing multi-task composition through an intuitive schema-based interface. Our experiments demonstrate competitive performance across extraction and classification tasks with substantial improvements in deployment accessibility compared to LLM-based alternatives. We release GLiNER2 as an open-source pip-installable library with pre-trained models and documentation at https://github.com/fastino-ai/GLiNER2. |
| title | GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.18546 |