| Automated Concatenation of Embeddings for Structured Prediction | ✓ Link | 94.6 | ACE + document-context | 2020-10-10 |
| LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention | ✓ Link | 94.3 | LUKE 483M | 2020-10-02 |
| Learning from Noisy Labels for Entity-Centric Information Extraction | ✓ Link | 94.22 | Co-regularized LUKE | 2021-04-17 |
| SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization | ✓ Link | 94.2 | LUKE + SubRegWeigh (K-means) | 2024-09-10 |
| Autoregressive Structured Prediction with Language Models | ✓ Link | 94.1 | ASP+T5-3B | 2022-10-26 |
| FLERT: Document-Level Features for Named Entity Recognition | ✓ Link | 94.09 | FLERT XLM-R | 2020-11-13 |
| Packed Levitated Marker for Entity and Relation Extraction | ✓ Link | 94.0 | PL-Marker | 2021-09-13 |
| Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning | ✓ Link | 93.85 | CL-KL | 2021-05-08 |
| Named entity recognition architecture combining contextual and global features | ✓ Link | 93.82 | XLNet-GCN | 2021-12-15 |
| SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization | ✓ Link | 93.81 | RoBERTa + SubRegWeigh (K-means) | 2024-09-10 |
| Autoregressive Structured Prediction with Language Models | ✓ Link | 93.8 | ASP+flan-T5-large | 2022-10-26 |
| InferNER: an attentive model leveraging the sentence-level information for Named Entity Recognition in Microblogs | | 93.76 | InferNER | 2021-04-18 |
| Exploring Cross-sentence Contexts for Named Entity Recognition with BERT | ✓ Link | 93.74 | Cross-sentence context (First) | 2020-06-02 |
| Transformer-based Named Entity Recognition with Combined Data Representation | | 93.69 | XLM-RoBERTa-large union | 2024-06-25 |
| Boundary Smoothing for Named Entity Recognition | ✓ Link | 93.65 | Baseline + BS | 2022-04-26 |
| Automated Concatenation of Embeddings for Structured Prediction | ✓ Link | 93.64 | ACE | 2020-10-10 |
| Focusing on Potential Named Entities During Active Label Acquisition | ✓ Link | 93.6 | BERT-CRF | 2021-11-06 |
| Cloze-driven Pretraining of Self-attention Networks | | 93.5 | CNN Large + fine-tune | 2019-03-19 |
| Named Entity Recognition as Dependency Parsing | ✓ Link | 93.5 | Biaffine-NER | 2020-05-14 |
| GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling | ✓ Link | 93.47 | GCDT + BERT-L | 2019-06-06 |
| Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition | ✓ Link | 93.47 | I-DARTS + Flair | 2019-11-01 |
| CrossWeigh: Training Named Entity Tagger from Imperfect Annotations | ✓ Link | 93.43 | CrossWeigh + Pooled Flair | 2019-09-03 |
| Neural Architectures for Nested NER through Linearization | ✓ Link | 93.38 | LSTM-CRF+ELMo+BERT+Flair | 2019-08-19 |
| Hierarchical Contextualized Representation for Named Entity Recognition | ✓ Link | 93.37 | Hierarchical + BERT | 2019-11-06 |
| Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning | ✓ Link | 93.35 | BERT-CRF (Replicated in AdaSeq) | 2021-05-08 |
| Dice Loss for Data-imbalanced NLP Tasks | ✓ Link | 93.33 | BERT-MRC+DSC | 2019-11-07 |
| Named entity recognition architecture combining contextual and global features | ✓ Link | 93.28 | XLNet | 2021-12-15 |
| A Unified Generative Framework for Various NER Subtasks | ✓ Link | 93.24 | BARTNER | 2021-06-02 |
| GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction | ✓ Link | 93.1 | GoLLIE | 2023-10-05 |
| Contextual String Embeddings for Sequence Labeling | ✓ Link | 93.09 | Flair embeddings | 2018-08-01 |
| PromptNER: Prompt Locating and Typing for Named Entity Recognition | ✓ Link | 93.08 | PromptNER [RoBERTa-large] | 2023-05-26 |
| Unified Named Entity Recognition as Word-Word Relation Classification | ✓ Link | 93.07 | W2NER | 2021-12-19 |
| A Unified MRC Framework for Named Entity Recognition | ✓ Link | 93.04 | BERT-MRC | 2019-10-25 |
| Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition | ✓ Link | 92.94 | Locate and Label | 2021-05-14 |
| Parallel Instance Query Network for Named Entity Recognition | ✓ Link | 92.87 | PIQN | 2022-03-20 |
| DiffusionNER: Boundary Diffusion for Named Entity Recognition | ✓ Link | 92.78 | DiffusionNER | 2023-05-22 |
| Towards Improving Neural Named Entity Recognition with Gazetteers | ✓ Link | 92.75 | HSCRF + softdict | 2019-07-01 |
| TENER: Adapting Transformer Encoder for Named Entity Recognition | ✓ Link | 92.62 | TENER | 2019-11-10 |
| Semi-Supervised Sequence Modeling with Cross-View Training | ✓ Link | 92.61 | CVT + Multi-Task | 2018-09-22 |
| Semi-Supervised Sequence Modeling with Cross-View Training | ✓ Link | 92.61 | CVT + Multi-Task + Large | 2018-09-22 |
| Joint Learning of Named Entity Recognition and Entity Linking | | 92.43 | Stack LSTM | 2019-07-18 |
| PromptNER: Prompt Locating and Typing for Named Entity Recognition | ✓ Link | 92.41 | PromptNER [BERT-large] | 2023-05-26 |
| Dependency-Guided LSTM-CRF for Named Entity Recognition | ✓ Link | 92.4 | DGLSTM-CRF + ELMo (L=2) 3.0pt1-4.51.5 | 2019-09-23 |
| GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition | ✓ Link | 92.34 | GRN | 2019-07-12 |
| Evaluating the Utility of Hand-crafted Features in Sequence Labelling | ✓ Link | 92.29 | Neural-CRF+AE | 2018-08-28 |
| Multi-Grained Named Entity Recognition | ✓ Link | 92.28 | MGNER | 2019-06-20 |
| Deep contextualized word representations | ✓ Link | 92.22 | BiLSTM-CRF+ELMo | 2018-02-15 |
| Generalizing Natural Language Analysis through Span-relation Representations | ✓ Link | 92.2 | SpanRel | 2019-11-10 |
| Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling | ✓ Link | 92.03 | LD-Net | 2018-04-20 |
| GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling | ✓ Link | 91.96 | GCDT | 2019-06-06 |
| Hierarchical Contextualized Representation for Named Entity Recognition | ✓ Link | 91.96 | Hierarchical | 2019-11-06 |
| Evaluating the Utility of Hand-crafted Features in Sequence Labelling | ✓ Link | 91.87 | CRF + AutoEncoder | 2018-08-28 |
| A Prism Module for Semantic Disentanglement in Name Entity Recognition | ✓ Link | 91.8 | PRISM | 2019-07-01 |
| []() | | 91.74 | GraphIE (GCN+BiLSTM) | |
| Robust Lexical Features for Improved Neural Network Named-Entity Recognition | ✓ Link | 91.73 | Bi-LSTM-CRF + Lexical Features | 2018-06-09 |
| Learning Better Internal Structure of Words for Sequence Labeling | | 91.64 | IntNet + BiLSTM-CRF | 2018-10-29 |
| Neural Reranking for Named Entity Recognition | ✓ Link | 91.62 | Yang et al. ([2017a]) | 2017-07-17 |
| Named Entity Recognition with Bidirectional LSTM-CNNs | ✓ Link | 91.62 | Bi-LSTM-CNN | 2015-11-26 |
| Sentence-State LSTM for Text Representation | ✓ Link | 91.57 | S-LSTM | 2018-05-07 |
| Long Short-Term Memory with Dynamic Skip Connections | ✓ Link | 91.56 | LSTM with dynamic skip | 2018-11-09 |
| Robust Multilingual Part-of-Speech Tagging via Adversarial Training | ✓ Link | 91.56 | Adversarial Bi-LSTM | 2017-11-14 |
| Hybrid semi-Markov CRF for Neural Sequence Labeling | ✓ Link | 91.38 | HSCRF | 2018-05-10 |
| Robust Multilingual Named Entity Recognition with Shallow Semi-Supervised Features | ✓ Link | 91.36 | IXA pipes | 2017-01-31 |
| NCRF++: An Open-source Neural Sequence Labeling Toolkit | ✓ Link | 91.35 | NCRF++ | 2018-06-14 |
| Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks | ✓ Link | 91.26 | Yang et al. | 2017-03-18 |
| Empower Sequence Labeling with Task-Aware Neural Language Model | ✓ Link | 91.24 | LM-LSTM-CRF | 2017-09-13 |
| A Deep Neural Network Model for the Task of Named Entity Recognition | ✓ Link | 91.22 | Bi-LSTM-CNN-CRF | 2018-02-01 |
| End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF | ✓ Link | 91.21 | BLSTM-CNN-CRF | 2016-03-04 |
| Harnessing Deep Neural Networks with Logic Rules | ✓ Link | 91.18 | Bi-LSTM + Logic rules | 2016-03-21 |
| Neural Architectures for Named Entity Recognition | ✓ Link | 90.94 | LSTM-CRF | 2016-03-04 |
| Named entity recognition architecture combining contextual and global features | ✓ Link | 88.63 | GCN | 2021-12-15 |
| Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms | ✓ Link | 86.28 | SWEM-CRF | 2018-05-24 |
| Variational Sequential Labelers for Semi-Supervised Learning | ✓ Link | 84.7 | VSL-GG-Hier | 2019-06-23 |