arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07575cs.CLcs.AIcs.IR
收藏

半监督关系抽取研究综述

A Review on Semi-Supervised Relation Extraction

University of Maryland(马里兰大学)

Yusen Lin

摘要:

关系抽取是从非结构化文本中抽取知识的重要方法,但需要大量的标注语料。为了减少昂贵的注释工作,半监督学习旨在利用标记和未标记的数据。在本文中,我们回顾和比较了三种典型的方法在半监督RE与深度学习或元学习:自集成,这迫使一致的扰动下,但可能会面临监督不足;自训练,迭代生成伪标签,并重新训练自己与扩大的标记集;双学习,利用一个原始任务和一个双任务,以提供相互反馈。平均教师(Tarvainen和Valpola,2017),LST(Li等人,2019)和DualRE(Lin et al.,2019)为代表,分别阐述了这三种方法的不足。

英文摘要:

Relation extraction (RE) plays an important role in extracting knowledge from unstructured text but requires a large amount of labeled corpus. To reduce the expensive annotation efforts, semisupervised learning aims to leverage both labeled and unlabeled data. In this paper, we review and compare three typical methods in semi-supervised RE with deep learning or meta-learning: self-ensembling, which forces consistent under perturbations but may confront insufficient supervision; self-training, which iteratively generates pseudo labels and retrain itself with the enlarged labeled set; dual learning, which leverages a primal task and a dual task to give mutual feedback. Mean-teacher (Tarvainen and Valpola, 2017), LST (Li et al., 2019), and DualRE (Lin et al., 2019) are elaborated as the representatives to alleviate the weakness of these three methods, respectively.

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。

↑