Improving Discriminative Learning for Zero-Shot Relation Extraction
Improving Discriminative Learning for Zero-Shot Relation Extraction
复制标题
DOI：
10.18653/v1/2022.spanlp-1.1
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Van-Hien Tran;Hiroki Ouchi;Taro Watanabe;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Van-Hien Tran;Hiroki Ouchi;Taro Watanabe;Yuji Matsumoto
零射击关系提取（Zero-shot relation extraction， ZSRE）旨在预测训练中无法观察到的目标关系。虽然以前的大多数研究都集中在完全监督关系提取上，并取得了相当高的性能，但对ZSRE的研究却很少。本研究提出了一种结合句子和语义关系的判别嵌入学习的新模型。此外，使用自适应比较器网络来判断句子与关系之间的关系是否一致。在两个基准数据集上的实验结果表明，该方法明显优于现有的方法。
Zero-shot relation extraction (ZSRE) aims to predict target relations that cannot be observed during training. While most previous studies have focused on fully supervised relation extraction and achieved considerably high performance, less effort has been made towards ZSRE. This study proposes a new model incorporating discriminative embedding learning for both sentences and semantic relations. In addition, a self-adaptive comparator network is used to judge whether the relationship between a sentence and a relation is consistent. Experimental results on two benchmark datasets showed that the proposed method significantly outperforms the state-of-the-art methods.