mlsanityData to 14 Oct 2026

HIORE: Leveraging High-order Interactions for Unified Entity Relation Extraction

arXiv 2305.04297 ↗First posted 7 May 2023cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Entity relation extraction consists of two sub-tasks: entity recognition and relation extraction. Existing methods either tackle these two tasks separately or unify them with word-by-word interactions. In this paper, we propose HIORE, a new method for unified entity relation extraction. The key insight is to leverage the high-order interactions, i.e., the complex association among word pairs, which contains richer information than the first-order word-by-word interactions. For this purpose, we first devise a W-shape DNN (WNet) to capture coarse-level high-order connections. Then, we build a heuristic high-order graph and further calibrate the representations with a graph neural network (GNN). Experiments on three benchmarks (ACE04, ACE05, SciERC) show that HIORE achieves the state-of-the-art performance on relation extraction and an improvement of 1.1~1.8 F1 points over the prior best unified model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 7 May 2023.

Builds on

19 of 33 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  4. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 322
  5. 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
  6. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  7. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  8. 2017Joint Extraction of Entities and Relations Based on a Novel Tagging Schemecited by 102
  9. 2019Entity-Relation Extraction as Multi-Turn Question Answeringcited by 96
  10. 2019A General Framework for Information Extraction using Dynamic Span Graphscited by 93
  11. 2020Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoderscited by 87
  12. 2021Document-level Relation Extraction as Semantic Segmentationcited by 80
7 more
  1. 2019Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extractioncited by 73
  2. 2020TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linkingcited by 72
  3. 2017Graph Convolutional Encoders for Syntax-aware Neural Machine Translationcited by 70
  4. 2018A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Taskscited by 54
  5. 2021UniRE: A Unified Label Space for Entity Relation Extractioncited by 38
  6. 2020Incomplete Utterance Rewriting as Semantic Segmentationcited by 33
  7. 2020Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extractioncited by 27

Built on by

Not cited yet.