mlsanityData to 7 Oct 2026

Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modeling

arXiv 2211.05343 ↗First posted 10 Nov 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a single document. One major challenge of DocRE is to dig decisive details regarding a specific entity pair from long text. However, in many cases, only a fraction of text carries required information, even in the manually labeled supporting evidence. To better capture and exploit instructive information, we propose a novel expLicit syntAx Refinement and Subsentence mOdeliNg based framework (LARSON). By introducing extra syntactic information, LARSON can model subsentences of arbitrary granularity and efficiently screen instructive ones. Moreover, we incorporate refined syntax into text representations which further improves the performance of LARSON. Experimental results on three benchmark datasets (DocRED, CDR, and GDA) demonstrate that LARSON significantly outperforms existing methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

33 of 49 references.

References · 33

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2019Simplifying Graph Convolutional Networkscited by 1,470
  6. 2021How Attentive are Graph Attention Networks?cited by 818
  7. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
  8. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  9. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  10. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  11. 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
  12. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
21 more
  1. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  2. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  3. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  4. 2020Coreferential Reasoning Learning for Language Representationcited by 80
  5. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 80
  6. 2021Document-level Relation Extraction as Semantic Segmentationcited by 80
  7. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  8. 2019Document-Level N-ary Relation Extraction with Multiscale Representation Learningcited by 52
  9. 2021Syntax-BERT: Improving Pre-trained Transformers with Syntax Treescited by 51
  10. 2020Global-to-Local Neural Networks for Document-Level Relation Extractioncited by 43
  11. 2019Fine-tune Bert for DocRED with Two-step Processcited by 42
  12. 2020HIN: Hierarchical Inference Network for Document-Level Relation Extractioncited by 42
  13. 2020Document-Level Relation Extraction with Reconstructioncited by 41
  14. 2021Relation Classification with Entity Type Restrictioncited by 31
  15. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  16. 2016Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentationcited by 26
  17. 2021Discriminative Reasoning for Document-level Relation Extractioncited by 25
  18. 2019Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understandingcited by 20
  19. 2018Neural Relation Extraction Within and Across Sentence Boundariescited by 13
  20. 2022Effective Few-Shot Named Entity Linking by Meta-Learningcited by 6
  21. 2022Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoningcited by 4

Built on by

Cited by year

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

4 papers.

  1. 2023RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extractioncited by 9
  2. 2022Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Frameworkcited by 6
  3. 2024FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extractioncited by 5
  4. 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussioncited by 1