mlsanityData to 7 Oct 2026

Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction

arXiv 2106.01793 ↗First posted 3 Jun 2021cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the relationship between a given entity pair. In this paper, we present an embarrassingly simple but effective method to heuristically select evidence sentences for document-level RE, which can be easily combined with BiLSTM to achieve good performance on benchmark datasets, even better than fancy graph neural network based methods. We have released our code at https://github.com/AndrewZhe/Three-Sentences-Are-All-You-Need.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 7 of its 19 references that are in the map. First posted on arXiv 3 Jun 2021.

Builds on

7 of 19 references.

References · 7

  1. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  2. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  3. 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
  4. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  5. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  6. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  7. 2016Distant Supervision for Relation Extraction beyond the Sentence Boundarycited by 62

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 5; 2024: 3; 2025: 1.

16 papers.

Sort:

  1. 2023DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extractioncited by 37
  2. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  3. 2022Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocREDcited by 19
  4. 2022What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classificationcited by 17
  5. 2022Document-Level Relation Extraction with Sentences Importance Estimation and Focusingcited by 16
  6. 2024Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extractioncited by 14
  7. 2022Multi-hop Evidence Retrieval for Cross-document Relation Extractioncited by 13
  8. 2023Uncertainty Guided Label Denoising for Document-level Distant Relation Extractioncited by 7
  9. 2021Modular Self-Supervision for Document-Level Relation Extractioncited by 4
  10. 2023Rethinking Document-Level Relation Extraction: A Reality Checkcited by 4
  11. 2023A Comprehensive Survey of Document-level Relation Extraction (2016-2023)cited by 4
  12. 2022Enhancing Document-level Relation Extraction by Entity Knowledge Injectioncited by 3
4 more
  1. 2023A Survey of Document-Level Information Extractioncited by 2
  2. 2024Reward-based Input Construction for Cross-document Relation Extractioncited by 1
  3. 2024GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extractioncited by 1
  4. 2025CDER: Collaborative Evidence Retrieval for Document-level Relation Extractioncited by 0