mlsanityData to 7 Oct 2026

GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction

arXiv 2205.03786 ↗First posted 8 May 2022cs.CL cs.AI cs.IRcited by 2

Not on the map. Why?

Abstract (arXiv)

Entity types and textual context are essential properties for sentence-level relation extraction (RE). Existing work only encodes these properties within individual instances, which limits the performance of RE given the insufficient features in a single sentence. In contrast, we model these properties from the whole dataset and use the dataset-level information to enrich the semantics of every instance. We propose the GRAPHCACHE (Graph Neural Network as Caching) module, that propagates the features across sentences to learn better representations for RE. GRAPHCACHE aggregates the features from sentences in the whole dataset to learn global representations of properties, and use them to augment the local features within individual sentences. The global property features act as dataset-level prior knowledge for RE, and a complement to the sentence-level features. Inspired by the classical caching technique in computer systems, we develop GRAPHCACHE to update the property representations in an online manner. Overall, GRAPHCACHE yields significant effectiveness gains on RE and enables efficient message passing across all sentences in the dataset.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 8 May 2022.

Builds on

35 of 47 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  11. 2018Graph Convolutional Networks for Text Classificationcited by 345
  12. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
23 more
  1. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 318
  2. 2019Knowledge Enhanced Contextual Word Representationscited by 294
  3. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 271
  4. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  5. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  6. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  7. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  8. 2020TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Taskcited by 96
  9. 2017Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a surveycited by 90
  10. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  11. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  12. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 80
  13. 2020Learning from Context or Names? An Empirical Study on Neural Relation Extractioncited by 75
  14. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  15. 2017Graph Convolutional Encoders for Syntax-aware Neural Machine Translationcited by 70
  16. 2020Dialogue-Based Relation Extractioncited by 68
  17. 2019SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominalscited by 63
  18. 2020Joint Constrained Learning for Event-Event Relation Extractioncited by 53
  19. 2019Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Networkcited by 51
  20. 2021Relation Classification with Entity Type Restrictioncited by 31
  21. 2020GDPNet: Refining Latent Multi-View Graph for Relation Extractioncited by 29
  22. 2019Graph Neural Networks with Generated Parameters for Relation Extractioncited by 27
  23. 2018Topic Memory Networks for Short Text Classificationcited by 25

Built on by

Cited by year

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

2 papers.

  1. 2022Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Constructioncited by 6
  2. 2023KEPLET: Knowledge-Enhanced Pretrained Language Model with Topic Entity Awarenesscited by 0