GLiNER多任务：通用轻量级模型用于各种信息提取任务

GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks

June 14, 2024

作者: Ihor Stepanov, Mykhailo Shtopko

cs.AI

摘要

信息抽取任务需要准确、高效和具有泛化能力的模型。经典的监督深度学习方法可以实现所需的性能，但它们需要大量数据集，并且在适应不同任务方面存在局限性。另一方面，大型语言模型（LLMs）展现出良好的泛化能力，意味着它们可以根据用户请求适应许多不同的任务。然而，LLMs 在计算上昂贵，并且往往无法生成结构化输出。在本文中，我们将介绍一种新型的GLiNER模型，可用于各种信息抽取任务，同时作为一个小型编码器模型。我们的模型在零-shot NER基准测试中取得了最先进的性能，并在问答、摘要和关系抽取任务中表现出色。此外，在本文中，我们将介绍使用GLiNER模型进行命名实体识别的自学习方法的实验结果。

English

Information extraction tasks require both accurate, efficient, and generalisable models. Classical supervised deep learning approaches can achieve the required performance, but they need large datasets and are limited in their ability to adapt to different tasks. On the other hand, large language models (LLMs) demonstrate good generalization, meaning that they can adapt to many different tasks based on user requests. However, LLMs are computationally expensive and tend to fail to generate structured outputs. In this article, we will introduce a new kind of GLiNER model that can be used for various information extraction tasks while being a small encoder model. Our model achieved SoTA performance on zero-shot NER benchmarks and leading performance on question-answering, summarization and relation extraction tasks. Additionally, in this article, we will cover experimental results on self-learning approaches for named entity recognition using GLiNER models.