[WWW2020 Honorable Mention Paper] ：NERO A Neural Rule Grounding Framework for Label-Efficient Relation Extraction
Deep neural models for relation extraction tend to be less reliable when perfectly labeled data is limited, despite their success in label sufficient scenarios.
当完全标记的数据有限时，用于关系提取的深层神经模型往往不太可靠，尽管它们在标记足够的场景中取得了成功。
Instead of seeking more instance-level labels from human annotators, here we propose to annotate frequent surface patterns to form labeling rules.
在这里，我们建议对频繁的表面模式进行注释，以形成标记规则，而不是从人类注释器中寻找更多的实例级标签。
In this paper,we present a neural approach to ground rules for RE, named Nero,which jointly learns a relation extraction module and a soft matching module.
本文提出了一种基于神经网络的RE基本规则学习方法，称为Nero，它联合学习关系抽取模块和软匹配模块。
当前常用关系提取方法示例
不同关系提取方法比较
NERO模型框架