mlsanityData to 7 Oct 2026

Mention-centered Graph Neural Network for Document-level Relation Extraction

arXiv 2103.08200 ↗First posted 15 Mar 2021cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Current approaches either leverage syntactic trees to construct document-level graphs or aggregate inference information from different sentences. In this paper, we build cross-sentence dependencies by inferring compositional relations between inter-sentence mentions. Adopting aggressive linking strategy, intermediate relations are reasoned on the document-level graphs by mention convolution. We further notice the generalization problem of NA instances, which is caused by incomplete annotation and worsened by fully-connected mention pairs. An improved ranking loss is proposed to attend this problem. Experiments show the connections between different mentions are crucial to document-level relation extraction, which enables the model to extract more meaningful higher-level compositional relations.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

20 of 37 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  3. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  4. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  5. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  6. 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
  7. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  8. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  9. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  10. 2016Distant Supervision for Relation Extraction beyond the Sentence Boundarycited by 62
  11. 2019Document-Level N-ary Relation Extraction with Multiscale Representation Learningcited by 52
  12. 2019Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Networkcited by 51
8 more
  1. 2018Reinforcement Learning for Relation Classification from Noisy Datacited by 46
  2. 2017Improved Neural Relation Detection for Knowledge Base Question Answeringcited by 44
  3. 2019Fine-tune Bert for DocRED with Two-step Processcited by 42
  4. 2020HIN: Hierarchical Inference Network for Document-Level Relation Extractioncited by 42
  5. 2015Classifying Relations by Ranking with Convolutional Neural Networkscited by 33
  6. 2018DSGAN: Generative Adversarial Training for Distant Supervision Relation Extractioncited by 23
  7. 2018Neural Relation Extraction Within and Across Sentence Boundariescited by 13
  8. 2018Multi-labeled Relation Extraction with Attentive Capsule Networkcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Multimodal learning with graphscited by 54