一个高效统一的文本信息抽取框架，支持多种任务。
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
- 基于模式驱动接口，用单一模型实现多任务信息抽取。
- 在多个任务上表现媲美大模型，且部署更轻便。
- 适合需要快速部署、资源受限场景的应用开发者。
信息抽取（IE）是众多自然语言处理应用的基础，但现有方案通常需为不同任务定制模型，或依赖计算开销大的大语言模型。我们提出 GLiNER2，一种统一框架，在保持原 GLiNER 架构优势的基础上，增强了对命名实体识别、文本分类和层次化结构数据抽取的支持。该模型基于预训练的 Transformer 编码器架构，兼具低内存占用与高推理效率，通过直观的模式驱动接口实现多任务组合。实验表明，其在各类抽取与分类任务中表现优异，相较于基于大语言模型的方案，部署门槛显著降低。我们已将 GLiNER2 以开源形式发布，可通过 pip 安装，包含预训练模型与文档，项目地址：https://github.com/fastino-ai/GLiNER2。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。