Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Christopoulou, Fenia; Misawa, Miwa; Ananiadou, Sophia

doi:10.18653/v1/d19-1498

Cited by 167 publications

(99 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this shortcoming, Verga et al ( 2018 ) form pairwise predictions over multiple sentences using a self-attention encoder, and aggregate the predictions by multi-instance learning. Christopoulou et al ( 2019a ) use an edge-oriented graph neural model to learn the representation of mention pairs. Nan et al ( 2020 ) develop a refinement strategy to automatically induce the latent document-level graph, which helps to reason relations across sentences.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, many approaches are proposed to address this problem. Christopoulou et al ( 2019a ) is one of the most powerful systems, which use an edge-oriented graph (EoG) neural model to learn the representation of mention pairs.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose an effective Graph Convolutional Networks (GCNs) for CID relation extraction (CID-GCN). Similar to Christopoulou et al ( 2019a ), we construct a heterogeneous graph which contains mention, sentence and entity nodes. By processing all the entities and mention nodes in the document in a unified manner, the intra- and inter-sentence relation facts can be extracted simultaneously in a model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction

2021

View full text Add to dashboard Cite

Automatic extraction of chemical-induced disease (CID) relation from unstructured text is of essential importance for disease treatment and drug development. In this task, some relational facts can only be inferred from the document rather than single sentence. Recently, researchers investigate graph-based approaches to extract relations across sentences. It iteratively combines the information from neighbor nodes to model the interactions in entity mentions that exist in different sentences. Despite their success, one severe limitation of the graph-based approaches is the over-smoothing problem, which decreases the model distinguishing ability. In this paper, we propose CID-GCN, an effective Graph Convolutional Networks (GCNs) with gating mechanism, for CID relation extraction. Specifically, we construct a heterogeneous graph which contains mention, sentence and entity nodes. Then, the graph convolution operation is employed to aggregate interactive information on the constructed graph. Particularly, we combine gating mechanism with the graph convolution operation to address the over-smoothing problem. The experimental results demonstrate that our approach significantly outperforms the baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction

2021

View full text Add to dashboard Cite

show abstract

“…Christopoulou et al [8] construct a new type of graph with MM (Mention-Mention), MS (Mention-Sentence), ME (Mention-Entity), SS (Sentence-Sentence) and encode it with an inference layer. They extract relations with the whole paragraph encoding.…”

Section: Binary Relation Extractionmentioning

confidence: 99%

“…They also extract relations with the whole paragraph encoding. The above two methods [8,33] neither consider link between entities nor reflect various discourse relations between sentences.…”

Section: Binary Relation Extractionmentioning

confidence: 99%

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Lee

Seo

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task. CCS CONCEPTS • Computing methodologies → Information extraction.

show abstract

Densely Connected Graph Attention Network Based on Iterative Path Reasoning for Document-Level Relation Extraction

Hong-ya

Huang

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Cited by 167 publications

References 39 publications

CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction

CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction

Cross-sentence N-ary Relation Extraction using Entity Link and Discourse Relation

Densely Connected Graph Attention Network Based on Iterative Path Reasoning for Document-Level Relation Extraction

Contact Info

Product

Resources

About