GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
This work addresses the need for more accessible and efficient information extraction tools for NLP practitioners, though it appears incremental as it builds on the original GLiNER architecture.
The paper tackles the problem of inefficient and specialized information extraction in NLP by presenting GLiNER2, a unified framework that supports multiple tasks like named entity recognition and text classification within a single efficient model, achieving competitive performance with improved deployment accessibility compared to large language model alternatives.
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.