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.

介绍一种新型 GLiNER 模型，用于各种信息提取任务，同时作为一个小型编码器模型。该模型在零样本 NER 基准测试上达到了最佳性能，并在问答、摘要和关系抽取任务上具有领先的性能。此外，本文还涵盖了使用 GLiNER 模型进行命名实体识别的自学习方法的实验结果。