A systematic review of relation extraction task since the emergence of Transformers

2025/11/05 by Célian Ringwald, Fabien Gandon, Celian, Ringwald +5
Computer Science · #A.1 #Benchmark (surveying) #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.4 #I.2.7 #Natural Language Processing Techniques #Relation (database) #Semantic Web #Systematic review #Task (project management) #Text Readability and Simplification #Topic Modeling #Transformer

paper · pdf · doi:10.48550/arxiv.2511.03610

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/11/05 · openalex created_date 2025/11/07 · openalex updated_date 2026/07/28

Abstract

This article presents a systematic review of relation extraction (RE) research since the advent of Transformer-based models. Using an automated framework to collect and annotate publications, we analyze 34 surveys, 64 datasets, and 104 models published between 2019 and 2024. The review highlights methodological advances, benchmark resources, and the integration of semantic web technologies. By consolidating results across multiple dimensions, the study identifies current trends, limitations, and open challenges, offering researchers and practitioners a comprehensive reference for understanding the evolution and future directions of RE.

Citations

• Small Language Models are the Future of Agentic AI
• Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities
• How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency
• Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition
• Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
• Benchmarking the Abilities of Large Language Models for RDF Knowledge Graph Creation and Comprehension: How Well Do LLMs Speak Turtle?
• RED^{\rm FM}: a Filtered and Multilingual Relation Extraction Dataset
• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction
• DocRED-FE: A Document-Level Fine-Grained Entity And Relation Extraction Dataset
• Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction
• A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach
• MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
• DORE: Document Ordered Relation Extraction based on Generative Framework
• KnowGL: Knowledge Generation and Linking from Text
• Generative Knowledge Graph Construction: A Review
• CrossRE: A Cross-Domain Dataset for Relation Extraction
• A Decade of Knowledge Graphs in Natural Language Processing: A Survey
• Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
• DeepStruct: Pretraining of Language Models for Structure Prediction
• WDV: A Broad Data Verbalisation Dataset Built from Wikidata
• What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification
• Unified Structure Generation for Universal Information Extraction
• RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction
• ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification
• Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
• Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey
• GenIE: Generative Information Extraction
• Learning Logic Rules for Document-level Relation Extraction
• Extracting Event Temporal Relations via Hyperbolic Geometry
• Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction
• A Partition Filter Network for Joint Entity and Relation Extraction
• ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models
• Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution
• Document-level Relation Extraction as Semantic Segmentation
• WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
• Improving BERT Model Using Contrastive Learning for Biomedical Relation Extraction
• Multi-view Inference for Relation Extraction with Uncertain Knowledge
• Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
• Re-TACRED: Addressing Shortcomings of the TACRED Dataset
• Document-Level Event Argument Extraction by Conditional Generation
• ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning
• Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings
• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction
• ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
• Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction
• Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
• Semi-supervised Relation Extraction via Incremental Meta Self-Training
• Learning from Context or Names? An Empirical Study on Neural Relation Extraction
• LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
• DWIE: an entity-centric dataset for multi-task document-level information extraction
• KILT: a Benchmark for Knowledge Intensive Language Tasks
• Language Models are Few-Shot Learners
• ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages
• SciREX: A Challenge Dataset for Document-Level Information Extraction
• Revisiting Unsupervised Relation Extraction
• Coreferential Reasoning Learning for Language Representation
• TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task
• Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations
• Are Noisy Sentences Useless for Distant Supervised Relation Extraction?
• Effective Modeling of Encoder-Decoder Architecture for Joint Entity and\n Relation Extraction
• FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
• Entity, Relation, and Event Extraction with Contextualized Span Representations
• Language Models as Knowledge Bases?
• Neural Snowball for Few-Shot Relation Learning
• X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension
• DocRED: A Large-Scale Document-Level Relation Extraction Dataset
• Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets
• Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction
• Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions
• Sentence Embedding Alignment for Lifelong Relation Extraction
• Learning Dual Retrieval Module for Semi-supervised Relation Extraction
• A Hierarchical Framework for Relation Extraction with Reinforcement Learning
• FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
• Which Knowledge Graph Is Best for Me?
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
• Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention
• A Multi-Axis Annotation Scheme for Event Temporal Relations
• A Structured Learning Approach to Temporal Relation Extraction
• Attention Is All You Need
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
• What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification
• A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers
• Transformer Enhanced Relation Classification: A Comparative Analysis of Contextuality, Data Efficiency and Sequence Complexity
• Relation of the Relations: A New Paradigm of the Relation Extraction Problem