Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction

Proceedings of the 28th International Conference on Computational Linguistics, pages 5259–5270 Barcelona, Spain (Online), December 8-13, 2020 5259 Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction Huiwei Zhou, Yibin Xu, Zhe Liu, Weihong Yao*, Chengkun Lang, Haibin Jiang School of Computer Science and Technology, Dalian University of Technology, China {zhouhuiwei, weihongy}@dlut.edu.cn {19xyb, njjnlz, kunkun, jianghaibin}@mail.dlut.edu.cn  Abstract Document-level Relation Extraction (RE) is particularly challenging due to complex semantic interactions among multiple entities in a document. Among exiting approaches, Graph Convo- lutional Networks (GCN) is one of the most effective approaches for document-level RE. How- ever, traditional GCN simply takes word nodes and adjacency matrix to represent graphs, which is difficult to establish direct connections between distant entity pairs. In this paper, we propose Global Context-enhanced Graph Convolutional Networks (GCGCN), a novel model which is composed of entities as nodes and context of entity pairs as edges between nodes to capture rich global context information of entities in a document. Two hierarchical blocks, Context-aware Attention Guided Graph Convolution (CAGGC) for partially connected graphs and Multi-head Attention Guided Graph Convolution (MAGGC) for fully connected graphs, could take pro- gressively more global context into account. Meantime, we leverage a large-scale distantly su- pervised dataset to pre-train a GCGCN model with curriculum learning, which is then fine-tuned on the human-annotated dataset for further improving document-level RE performance. The experimental results on DocRED show that our model could effectively capture rich global con- text information in the document, leading to a state-of-the-art result. Our code is available at https://github.com/Huiweizhou/GCGCN. 1 Introduction The task of Relation Extraction (RE) aims to detect semantic relations among entities in text, which plays an important role in many natural language processing applications such as knowledge discovery (Quirk and Poon, 2017), and question answering (Yih et al., 2015; Yu et al., 2017). Previous research on relation extraction mainly focuses on sentence-level, i.e., predicting relations between entity pairs in a given sentence. However, in real-world scenarios, many relations are expressed across sentences. The task of identifying these relations is named inter-sentence RE. Typically, inter- sentence relations occur in textual snippets with several sentences, such as documents. In a document, multiple mentions of the target entities in different sentences should be used for inter-sentence relation extraction, since their relations are expressed through the interactions of these mentions in the whole document. Yao et al. (2019) introduce a dataset called DocRED to accelerate the research on document-level RE. Take a document from DocRED as an example in Figure 1.There are many simple intra-sentence rela- tions, such as (“Ikwilalles met je delen”, entry song, Eurovision Song Contest 1990) in sentence 1, (“Ikwilalles met je delen”, performed after, “Quand je terêve”) and (Céline Carzo, performer, “Quand je terêve”) in sentence 5. Only one evidence sentence is needed to predict these relation facts. However, the inter-sentence relation (Céline Carzo, participant of, Eurovision Song Contest 1990) is supported by two evidence sentences (sentence 1 and sentence 5), and should be inferred based on the above three This …

Content truncated to 500 words