mlsanityData to 13 Oct 2026

FLERT: Document-Level Features for Named Entity Recognition

arXiv 2011.06993 ↗First posted 13 Nov 2020cs.CLcited by 45

Not on the map. Why?

Abstract (arXiv)

Current state-of-the-art approaches for named entity recognition (NER) typically consider text at the sentence-level and thus do not model information that crosses sentence boundaries. However, the use of transformer-based models for NER offers natural options for capturing document-level features. In this paper, we perform a comparative evaluation of document-level features in the two standard NER architectures commonly considered in the literature, namely "fine-tuning" and "feature-based LSTM-CRF". We evaluate different hyperparameters for document-level features such as context window size and enforcing document-locality. We present experiments from which we derive recommendations for how to model document context and present new state-of-the-art scores on several CoNLL-03 benchmark datasets. Our approach is integrated into the Flair framework to facilitate reproduction of our experiments.

Key facts. Cited by 45 papers in the map (data through 13 Oct 2026). First posted on arXiv 13 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 16; 2024: 10; 2025: 0; 2026: 4.

45 papers.

Sort:

By area:

  1. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 169
  2. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 56
  3. 2021ExplainaBoard: An Explainable Leaderboard for NLPcited by 50
  4. 2024Reverse Training to Nurse the Reversal Cursecited by 49
  5. 2023Retrieval-Augmented Code Generation for Universal Information Extractioncited by 40
  6. 2024Learnable Privacy Neurons Localization in Language Modelscited by 27
  7. 2021ITA: Image-Text Alignments for Multi-Modal Named Entity Recognitioncited by 24
  8. 2022Location reference recognition from texts: A survey and comparisoncited by 17
  9. 2023FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval systemcited by 15
  10. 2023Time for aCTIon: Automated Analysis of Cyber Threat Intelligence in the Wildcited by 15
  11. 2024Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model promptingcited by 12
  12. 2023CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Datasetcited by 11
33 more
  1. 2023In the Name of Fairness: Assessing the Bias in Clinical Record De-identificationcited by 9
  2. 2022hmBERT: Historical Multilingual Language Models for Named Entity Recognitioncited by 8
  3. 2021CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domaincited by 7
  4. 2023Examining risks of racial biases in NLP tools for child protective servicescited by 6
  5. 2021Regularization for Long Named Entity Recognitioncited by 5
  6. 2023Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationesecited by 5
  7. 2022From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern Frenchcited by 4
  8. 2022Evaluation of Embedding Models for Automatic Extraction and Classification of Acknowledged Entities in Scientific Documentscited by 3
  9. 2023SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoningcited by 3
  10. 2024Do "English" Named Entity Recognizers Work Well on Global Englishes?cited by 2
  11. 2024CoNLL#: Fine-grained Error Analysis and a Corrected Test Set for CoNLL-03 Englishcited by 2
  12. 2024Annotations for Exploring Food Tweets From Multiple Aspectscited by 2
  13. 2022Multilinguals at SemEval-2022 Task 11: Complex NER in Semantically Ambiguous Settings for Low Resource Languagescited by 1
  14. 2022Multilingual Name Entity Recognition and Intent Classification Employing Deep Learning Architecturescited by 1
  15. 2022Enriching Relation Extraction with OpenIEcited by 1
  16. 2023Comparing and combining some popular NER approaches on Biomedical taskscited by 1
  17. 2023An In-Context Schema Understanding Method for Knowledge Base Question Answeringcited by 1
  18. 2024Assisted Knowledge Graph Authoring: Human-Supervised Knowledge Graph Construction from Natural Languagecited by 1
  19. 2024NoiseBench: Benchmarking the Impact of Real Label Noise on Named Entity Recognitioncited by 1
  20. 2026DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal informationcited by 1
  21. 2021Named Entity Recognition and Linking Augmented with Large-Scale Structured Datacited by 0
  22. 2022Low Resource Pipeline for Spoken Language Understanding via Weak Supervisioncited by 0
  23. 2022BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graphcited by 0
  24. 2022MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languagescited by 0
  25. 2023Automated Labeling of German Chest X-Ray Radiology Reports using Deep Learningcited by 0
  26. 2023Transfer Learning across Several Centuries: Machine and Historian Integrated Method to Decipher Royal Secretary's Diarycited by 0
  27. 2023Embedding Models for Supervised Automatic Extraction and Classification of Named Entities in Scientific Acknowledgementscited by 0
  28. 2023A Few-Shot Learning Focused Survey on Recent Named Entity Recognition and Relation Classification Methodscited by 0
  29. 2024Fine Tuning Named Entity Extraction Models for the Fantasy Domaincited by 0
  30. 2024Question Answering Over Spatio-Temporal Knowledge Graphcited by 0
  31. 2026Explanation-Guided Medical Named Entity Recognition with Stability and Boundary Awareness for Atopic Dermatitiscited by 0
  32. 2026Knowledgeless Language Models: Suppressing Parametric Recall for Evidence-Grounded Language Modelingcited by 0
  33. 2026Redakto - The Incognito Tab for LLMscited by 0