arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.09145cs.CLcs.AI
收藏

ToNER:基于生成式语言模型的类型导向命名实体识别

ToNER: Type-oriented Named Entity Recognition with Generative Language Model

School of Data Science, Fudan University(复旦大学数据科学学院);Shanghai Key Laboratory of Data Science(上海市数据科学重点实验室)

Guochao Jiang, Ziqin Luo, Yuchen Shi, Dixuan Wang, Jiaqing Liang, Deqing Yang

AI总结:

本文提出生成式NER框架ToNER,通过类型匹配、多二分类和辅助任务充分利用实体类型信息,在多个基准上验证了其有效性。

摘要:

近年来,经过微调的生成式模型已被证明在命名实体识别(NER)任务上比以往基于标注或基于片段的方法更强大。同时也有研究发现,与实体相关的信息(例如实体类型)能够促使模型更好地完成 NER。然而,提前确定给定句子中实际存在的实体类型并不容易,而输入过多潜在的实体类型又不可避免地会分散模型的注意力。为了利用实体类型在提升 NER 任务上的优势,本文提出了一种新颖的 NER 框架,即基于生成式模型的 ToNER。在 ToNER 中,首先提出一个类型匹配模型,用于识别句子中最可能出现的实体类型。然后,我们附加一个多二分类任务来微调生成式模型的编码器,从而生成输入句子的精细化表示。此外,我们还增加了一个辅助任务,使模型能够发现实体类型,从而进一步微调模型以输出更准确的结果。我们在若干 NER 基准上的大量实验验证了 ToNER 中面向实体类型利用的所提策略的有效性。

英文摘要:

In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has also been found that the information related to entities, such as entity types, can prompt a model to achieve NER better. However, it is not easy to determine the entity types indeed existing in the given sentence in advance, and inputting too many potential entity types would distract the model inevitably. To exploit entity types' merit on promoting NER task, in this paper we propose a novel NER framework, namely ToNER based on a generative model. In ToNER, a type matching model is proposed at first to identify the entity types most likely to appear in the sentence. Then, we append a multiple binary classification task to fine-tune the generative model's encoder, so as to generate the refined representation of the input sentence. Moreover, we add an auxiliary task for the model to discover the entity types which further fine-tunes the model to output more accurate results. Our extensive experiments on some NER benchmarks verify the effectiveness of our proposed strategies in ToNER that are oriented towards entity types' exploitation.

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。

↑