arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.12925cs.LGcs.AIcs.CLcs.IR
收藏

GLiNER 多任务:适用于多种信息抽取任务的通用轻量级模型

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

Knowledgator Engineering LTD(Knowledgator工程有限公司)

Ihor Stepanov, Mykhailo Shtopko

AI总结:

本文提出一种小型编码器架构的 GLiNER 多任务模型,在零样本命名实体识别上达到最先进性能,并在问答、摘要和关系抽取等任务中表现领先,同时探索了基于自学习的命名实体识别方法。

摘要:

信息抽取任务既要求模型准确、高效,又要求其具备良好的泛化能力。传统的监督式深度学习方法能够达到所需性能,但它们需要大规模数据集,并且在适应不同任务方面能力有限。另一方面,大语言模型(LLMs)展现出良好的泛化性,意味着它们可以根据用户请求适应许多不同任务。然而,大语言模型计算开销高昂,并且往往难以生成结构化输出。在本文中,我们将介绍一种新型 GLiNER 模型,该模型可用于多种信息抽取任务,同时本身是一个小型编码器模型。我们的模型在零样本命名实体识别基准上取得了最先进(SoTA)性能,并在问答、摘要和关系抽取任务上取得了领先性能。此外,在本文中,我们还将介绍使用 GLiNER 模型进行命名实体识别自学习方法的实验结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑