mlsanityData to 7 Oct 2026

Unified Structure Generation for Universal Information Extraction

arXiv 2203.12277 ↗First posted 23 Mar 2022cs.CLcited by 220

Not on the map. Why?

Abstract (arXiv)

Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. In this paper, we propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism - structural schema instructor, and captures the common IE abilities via a large-scale pre-trained text-to-structure model. Experiments show that UIE achieved the state-of-the-art performance on 4 IE tasks, 13 datasets, and on all supervised, low-resource, and few-shot settings for a wide range of entity, relation, event and sentiment extraction tasks and their unification. These results verified the effectiveness, universality, and transferability of UIE.

Key facts. Cited by 220 papers in the map (data through 7 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

44 of 72 references.

References · 44

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  8. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  9. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  10. 2016Neural Architectures for Named Entity Recognitioncited by 548
  11. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  12. 2021Unifying Vision-and-Language Tasks via Text Generationcited by 411
32 more
  1. 2020Autoregressive Entity Retrievalcited by 333
  2. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  3. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  4. 2017End-to-end Neural Coreference Resolutioncited by 240
  5. 2020UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learningcited by 239
  6. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  7. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  8. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
  9. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  10. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  11. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  12. 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
  13. 2017Joint Extraction of Entities and Relations Based on a Novel Tagging Schemecited by 102
  14. 2021A Unified Generative Framework for Aspect-Based Sentiment Analysiscited by 97
  15. 2020Position-Aware Tagging for Aspect Sentiment Triplet Extractioncited by 90
  16. 2020Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoderscited by 87
  17. 2020TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linkingcited by 72
  18. 2020ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learningcited by 72
  19. 2021Learning Span-Level Interactions for Aspect Sentiment Triplet Extractioncited by 60
  20. 2019Neural Architectures for Nested NER through Linearizationcited by 56
  21. 2020Joint Entity and Relation Extraction with Set Prediction Networkscited by 54
  22. 2019Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategycited by 41
  23. 2021PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extractioncited by 40
  24. 2021CLEVE: Contrastive Pre-training for Event Extractioncited by 36
  25. 2019Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networkscited by 33
  26. 2020Coarse-to-Fine Pre-training for Named Entity Recognitioncited by 28
  27. 2020Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extractioncited by 27
  28. 2021Fine-grained Entity Typing via Label Reasoningcited by 22
  29. 2021Intent Classification and Slot Filling for Privacy Policiescited by 18
  30. 2018Nugget Proposal Networks for Chinese Event Detectioncited by 11
  31. 2020End-to-End Neural Event Coreference Resolutioncited by 10
  32. 2021HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extractioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 21; 2023: 75; 2024: 60; 2025: 30; 2026: 34.

220 papers.

Sort:

By area:

  1. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  2. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 222
  3. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  4. 2023Large Language Models for Generative Information Extraction: A Surveycited by 183
  5. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 167
  6. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  7. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  8. 2023GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extractioncited by 116
  9. 2023Revisiting Relation Extraction in the era of Large Language Modelscited by 100
  10. 2023GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformercited by 84
  11. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  12. 2023CodeIE: Large Code Generation Models are Better Few-Shot Information Extractorscited by 67
38 more
  1. 2022Generative Knowledge Graph Construction: A Reviewcited by 49
  2. 2023MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Predictioncited by 49
  3. 2023Universal Information Extraction as Unified Semantic Matchingcited by 47
  4. 2023LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Modelcited by 43
  5. 2023Retrieval-Augmented Code Generation for Universal Information Extractioncited by 40
  6. 2023PromptNER: Prompting For Named Entity Recognitioncited by 35
  7. 2024KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extractioncited by 33
  8. 2022A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systemscited by 32
  9. 2024BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicinecited by 30
  10. 2022Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generationcited by 28
  11. 2023CodeKGC: Code Language Model for Generative Knowledge Graph Constructioncited by 28
  12. 2023TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extractioncited by 27
  13. 2024Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labelingcited by 24
  14. 2024ADELIE: Aligning Large Language Models on Information Extractioncited by 24
  15. 2024C-ICL: Contrastive In-context Learning for Information Extractioncited by 22
  16. 2023Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuningcited by 21
  17. 2026Beyond Static Summarization: Proactive Memory Extraction for LLM Agentscited by 20
  18. 2023AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Modelcited by 19
  19. 2023YAYI-UIE: A Chat-Enhanced Instruction Tuning Framework for Universal Information Extractioncited by 19
  20. 2023SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understandingcited by 18
  21. 2023PromptNER: Prompt Locating and Typing for Named Entity Recognitioncited by 17
  22. 2024UMIE: Unified Multimodal Information Extraction with Instruction Tuningcited by 17
  23. 2023A Sequence-to-Sequence&Set Model for Text-to-Table Generationcited by 16
  24. 2024ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budgetcited by 16
  25. 2022Knowledge Graph Generation From Textcited by 15
  26. 2023FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Promptcited by 14
  27. 2024OAG-Bench: A Human-Curated Benchmark for Academic Graph Miningcited by 14
  28. 2024Aligning Large Language Models to a Domain-specific Graph Database for NL2GQLcited by 14
  29. 2024MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Taskscited by 14
  30. 2022Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graphcited by 13
  31. 2023A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promisescited by 13
  32. 2024gTBLS: Generating Tables from Text by Conditional Question Answeringcited by 13
  33. 2023ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Timecited by 12
  34. 2023Mirror: A Universal Framework for Various Information Extraction Taskscited by 12
  35. 2024Evolving Knowledge Distillation with Large Language Models and Active Learningcited by 12
  36. 2022Domain-Specific NER via Retrieving Correlated Samplescited by 11
  37. 2023InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Modelscited by 11
  38. 2023Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Constructioncited by 11

50 most cited of 220 All 220 (JSON)