mlsanityData to 14 Oct 2026

FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction

arXiv 2306.14913 ↗First posted 19 Jun 2023cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Universal Information Extraction (UIE) has been introduced as a unified framework for various Information Extraction (IE) tasks and has achieved widespread success. Despite this, UIE models have limitations. For example, they rely heavily on span boundaries in the data during training, which does not reflect the reality of span annotation challenges. Slight adjustments to positions can also meet requirements. Additionally, UIE models lack attention to the limited span length feature in IE. To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework. Specifically, our contribution consists of two concepts: fuzzy span loss and fuzzy span attention. Our experimental results on a series of main IE tasks show significant improvement compared to the baseline, especially in terms of fast convergence and strong performance with small amounts of data and training epochs. These results demonstrate the effectiveness and generalization of FSUIE in different tasks, settings, and scenarios.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 19 Jun 2023.

Builds on

29 of 44 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2018Deep contextualized word representationscited by 2,290
  5. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  6. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  7. 2019Massively Multilingual Neural Machine Translationcited by 246
  8. 2022Unified Structure Generation for Universal Information Extractioncited by 221
  9. 2019Adaptive Attention Span in Transformerscited by 149
  10. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  11. 2019Span-based Joint Entity and Relation Extraction with Transformer Pre-trainingcited by 133
  12. 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
17 more
  1. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  2. 2020Position-Aware Tagging for Aspect Sentiment Triplet Extractioncited by 91
  3. 2020Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoderscited by 87
  4. 2021A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysiscited by 62
  5. 2021Learning Span-Level Interactions for Aspect Sentiment Triplet Extractioncited by 60
  6. 2021Packed Levitated Marker for Entity and Relation Extractioncited by 49
  7. 2018Robust Distant Supervision Relation Extraction via Deep Reinforcement Learningcited by 35
  8. 2022Boundary Smoothing for Named Entity Recognitioncited by 22
  9. 2021Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inferencecited by 19
  10. 2021Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognitioncited by 18
  11. 2019Integrating Deep Learning with Logic Fusion for Information Extractioncited by 15
  12. 2022Global Pointer: Novel Efficient Span-based Approach for Named Entity Recognitioncited by 15
  13. 2021Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Modelcited by 13
  14. 2022A Span-level Bidirectional Network for Aspect Sentiment Triplet Extractioncited by 12
  15. 2020Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representationscited by 5
  16. 2021BoningKnife: Joint Entity Mention Detection and Typing for Nested NER via prior Boundary Knowledgecited by 2
  17. 2019Modeling Named Entity Embedding Distribution into Hyperspherecited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 2.

7 papers.

  1. 2024Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Surveycited by 16
  2. 2023A Novel Energy based Model Mechanism for Multi-modal Aspect-Based Sentiment Analysiscited by 3
  3. 2024A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decodercited by 1
  4. 2025Label Drop for Multi-Aspect Relation Modeling in Universal Information Extractioncited by 1
  5. 2025Dependency Structure Augmented Contextual Scoping Framework for Multimodal Aspect-Based Sentiment Analysiscited by 1
  6. 2024A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correctioncited by 0
  7. 2024RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLUcited by 0