mlsanityData to 7 Oct 2026

Few-Shot Document-Level Relation Extraction

arXiv 2205.02048 ↗First posted 4 May 2022cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online (https://github.com/nicpopovic/FREDo).

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 4 May 2022.

Builds on

17 of 28 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2016Matching Networks for One Shot Learningcited by 2,246
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  6. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 271
  7. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  8. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  9. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  10. 2020SciREX: A Challenge Dataset for Document-Level Information Extractioncited by 111
  11. 2019FewRel 2.0: Towards More Challenging Few-Shot Relation Classificationcited by 94
  12. 2021Document-level Relation Extraction as Semantic Segmentationcited by 80
5 more
  1. 2020Dialogue-Based Relation Extractioncited by 68
  2. 2021Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extractioncited by 68
  3. 2021Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemescited by 27
  4. 2021SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extractioncited by 23
  5. 2019Extracting Multiple-Relations in One-Pass with Pre-Trained Transformerscited by 19

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 3.

11 papers.

  1. 2024Automated Construction of Theme-specific Knowledge Graphscited by 15
  2. 2022Few-Shot Document-Level Event Argument Extractioncited by 9
  3. 2023RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extractioncited by 9
  4. 2023Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extractioncited by 5
  5. 2025Event Extraction in Large Language Modelcited by 5
  6. 2025GLiDRE: Generalist Lightweight model for Document-level Relation Extractioncited by 3
  7. 2023Silver Syntax Pre-training for Cross-Domain Relation Extractioncited by 2
  8. 2024TPN: Transferable Proto-Learning Network towards Few-shot Document-Level Relation Extractioncited by 1
  9. 2024Diversity Over Quantity: A Lesson From Few Shot Relation Classificationcited by 1
  10. 2025DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrationscited by 1
  11. 2024Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documentscited by 0