GenerativeRE: Incorporating a Novel Copy Mechanism and Pretrained Model for Joint Entity and Relation Extraction-猫眼课题宝

DOI：

10.18653/v1/2021.findings-emnlp.182

发表时间：

2021

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Jiarun Cao;S. Ananiadou

先前的神经seq2seq模型已经显示出联合提取关系三元组的有效性。然而，这些模型在从输入句子中提取多标记实体时存在不完整和无序问题。为了解决这些问题，我们提出了一个生成的，多任务的学习框架，命名为GenerativeRE。首先，我们提出了一种特殊的实体标记方法的输入和输出序列。在训练阶段，GenerativeRE对预训练的生成模型进行微调，同时学习特殊的实体标签。在推理阶段，我们提出了一种新的复制机制，配备了三个掩码策略，通过减少模型解码器的范围来生成最可能的令牌。实验结果表明，在NYT24和NYT29基准数据集上，该模型的F1得分分别比现有方法提高了4.6%和0.9%。

Previous neural seq2seq models have shown the e ﬀ ectiveness for jointly extracting relation triplets. However, most of these models suf-fer from incompletion and disorder problems when they extract multi-token entities from input sentences. To tackle these problems, we propose a generative, multi-task learning framework, named GenerativeRE. We ﬁrstly propose a special entity labelling method on both input and output sequences. During the training stage, GenerativeRE ﬁne-tunes the pretrained generative model and learns the special entity labels simultaneously. During the inference stage, we propose a novel copy mechanism equipped with three mask strategies, to generate the most probable tokens by diminishing the scope of the model decoder. Experimental results show that our model achieves 4.6% and 0.9% F1 score im-provements over the current state-of-the-art methods in the NYT24 and NYT29 benchmark datasets respectively.

GenerativeRE: Incorporating a Novel Copy Mechanism and Pretrained Model for Joint Entity and Relation Extraction

文献摘要

被引文献

相似文献