论文标题
用于文档级关系提取的蒙版图像重建网络
A Masked Image Reconstruction Network for Document-level Relation Extraction
论文作者
论文摘要
文档级别的关系提取旨在提取文档中实体之间的关系。与其句子级别的对应物相比，文档级关系提取需要对多个句子进行推断以提取复杂的关系三元组。先前的研究通常通过有关提及级别或实体级文档编写的信息传播来完成推理，而不管关系之间的相关性如何。在本文中，我们提出了一个基于掩盖图像重建网络（DRE-MIR）的新型文档级别关系提取模型，该模型将推断模型为掩盖的图像重建问题，以捕获关系之间的相关性。具体来说，我们首先利用编码器模块来获取实体的功能，并根据功能构建实体对矩阵。之后，我们将实体对矩阵视为图像，然后随机掩盖它并通过推理模块恢复它以捕获关系之间的相关性。我们在三个公共文档级关系提取数据集（即Docred，CDR和GDA）上评估了我们的模型。实验结果表明，我们的模型在这三个数据集上实现了最先进的性能，并且在推理过程中对噪声具有出色的鲁棒性。
Document-level relation extraction aims to extract relations among entities within a document. Compared with its sentence-level counterpart, Document-level relation extraction requires inference over multiple sentences to extract complex relational triples. Previous research normally complete reasoning through information propagation on the mention-level or entity-level document-graphs, regardless of the correlations between the relationships. In this paper, we propose a novel Document-level Relation Extraction model based on a Masked Image Reconstruction network (DRE-MIR), which models inference as a masked image reconstruction problem to capture the correlations between relationships. Specifically, we first leverage an encoder module to get the features of entities and construct the entity-pair matrix based on the features. After that, we look on the entity-pair matrix as an image and then randomly mask it and restore it through an inference module to capture the correlations between the relationships. We evaluate our model on three public document-level relation extraction datasets, i.e. DocRED, CDR, and GDA. Experimental results demonstrate that our model achieves state-of-the-art performance on these three datasets and has excellent robustness against the noises during the inference process.
