arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.02661cs.CL
收藏

Ask2Transformers:使用预训练语言模型的Zero-Shot域标记

Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models

HiTZ Center(HiTZ中心);University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU))

Oscar Sainz, German Rigau

摘要:

在本文中,我们提出了一个系统,利用不同的预先训练的语言模型分配域标签的WordNet同义词集没有任何形式的监督。此外,系统不限于使用特定的域标签集合。我们利用不同的现成的预训练语言模型和任务公式中编码的知识来推断特定WordNet定义的域标签。所提出的zero-shot系统在评估中使用的英语数据集上实现了新的最先进水平。

英文摘要:

In this paper we present a system that exploits different pre-trained Language Models for assigning domain labels to WordNet synsets without any kind of supervision. Furthermore, the system is not restricted to use a particular set of domain labels. We exploit the knowledge encoded within different off-the-shelf pre-trained Language Models and task formulations to infer the domain label of a particular WordNet definition. The proposed zero-shot system achieves a new state-of-the-art on the English dataset used in the evaluation.

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。

↑