Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Nan, Guoshun; Guo, Zhijiang; Sekulić, Ivan; Lu, Wei

doi:10.18653/v1/2020.acl-main.141

Cited by 218 publications

(200 citation statements)

References 55 publications

(58 reference statements)

Supporting

Mentioning

200

Contrasting

Order By: Relevance

“…[56] proposed a dataset for document-level relation extraction tasks, and summarized several types of relational reasoning like logical, coreference, common sense, and so on. Recently, many works like [57,58] have begun to tackle the problem of cross-sentence relational reasoning, which is an important research direction in the future.…”

Section: Discussionmentioning

confidence: 99%

Syntax-Informed Self-Attention Network for Span-Based Joint Entity and Relation Extraction

Zhang¹,

Zhang²,

Ma³

2021

Applied Sciences

View full text Add to dashboard Cite

Current state-of-the-art joint entity and relation extraction framework is based on span-level entity classification and relation identification between pairs of entity mentions. However, while maintaining an efficient exhaustive search on spans, the importance of syntactic features is not taken into consideration. It will lead to a problem that the prediction of a relation between two entities is related based on corresponding entity types, but in fact they are not related in the sentence. In addition, although previous works have proven that extract local context is beneficial for the task, it still lacks in-depth learning of contextual features in local context. In this paper, we propose to incorporate syntax knowledge into multi-head self-attention by employing part of heads to focus on syntactic parents of each token from pruned dependency trees, and we use it to model the global context to fuse syntactic and semantic features. In addition, in order to get richer contextual features from the local context, we apply local focus mechanism on entity pairs and corresponding context. Based on applying the two strategies, we perform joint entity and relation extraction on span-level. Experimental results show that our model achieves significant improvements on both Conll04 and SciERC dataset compared to strong competitors.

show abstract

Section: Discussionmentioning

confidence: 99%

Syntax-Informed Self-Attention Network for Span-Based Joint Entity and Relation Extraction

Zhang¹,

Zhang²,

Ma³

2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…(9) EoG (Christopoulou et al, 2019a ). (10) LSR (Nan et al, 2020 ). We use precision, recall, and F1 score to evaluate the performance.…”

Section: Methodsmentioning

confidence: 99%

“…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%

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

“…Previous work in document-level RE do not consider reasoning (Gupta et al, 2019;Jia et al, 2019;Yao et al, 2019), or only use graph-based or hierarchical neural network to conduct reasoning in an implicit way (Peng et al, 2017;Sahu et al, 2019;Nan et al, 2020). In this paper, we propose a Graph Aggregation-and-Inference Network (GAIN) for document-level relation extraction.…”

Section: Error Typementioning

confidence: 99%

Double Graph Based Reasoning for Document-level Relation Extraction

Zeng

Chang

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

157

121

View full text Add to dashboard Cite

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across paragraphs. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN), a method to recognize such relations for long paragraphs. GAIN constructs two graphs, a heterogeneous mentionlevel graph (MG) and an entity-level graph (EG). The former captures complex interaction among different mentions and the latter aggregates mentions underlying for the same entities. Based on the graphs we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/ PKUnlp-icler/GAIN.

show abstract

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Cited by 218 publications

References 55 publications

Syntax-Informed Self-Attention Network for Span-Based Joint Entity and Relation Extraction

Syntax-Informed Self-Attention Network for Span-Based Joint Entity and Relation Extraction

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

Double Graph Based Reasoning for Document-level Relation Extraction

Contact Info

Product

Resources

About