GLiNER多任務：針對各種資訊提取任務的通用輕量級模型

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

June 14, 2024

作者: Ihor Stepanov, Mykhailo Shtopko

cs.AI

摘要

資訊提取任務需要精確、高效且具有一般化的模型。傳統監督式深度學習方法可以達到所需的性能，但需要大量數據集，並且在適應不同任務方面存在限制。另一方面，大型語言模型（LLMs）展現出良好的泛化能力，意味著它們可以根據用戶的要求適應許多不同的任務。然而，LLMs在計算上昂貴且往往無法生成結構化輸出。在本文中，我們將介紹一種新型的GLiNER模型，可用於各種資訊提取任務，同時是一個小型編碼器模型。我們的模型在零-shot NER基準測試中取得了最先進的性能，並在問答、摘要和關係提取任務中表現卓越。此外，在本文中，我們將介紹使用GLiNER模型進行自我學習方法進行命名實體識別的實驗結果。

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.