mlsanityData to 14 Oct 2026

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

arXiv 2105.07148 ↗First posted 15 May 2021cs.CLcited by 34

Not on the map. Why?

Abstract (arXiv)

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random initialized sequence layer and do not integrate them into the bottom layers of BERT. In this paper, we propose Lexicon Enhanced BERT (LEBERT) for Chinese sequence labelling, which integrates external lexicon knowledge into BERT layers directly by a Lexicon Adapter layer. Compared with the existing methods, our model facilitates deep lexicon knowledge fusion at the lower layers of BERT. Experiments on ten Chinese datasets of three tasks including Named Entity Recognition, Word Segmentation, and Part-of-Speech tagging, show that LEBERT achieves the state-of-the-art results.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 24 of its 59 references that are in the map. First posted on arXiv 15 May 2021.

Builds on

24 of 59 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2016Neural Architectures for Named Entity Recognitioncited by 550
  4. 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 445
  5. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  6. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 319
  7. 2019ERNIE: Enhanced Representation through Knowledge Integrationcited by 302
  8. 2019Simple, Scalable Adaptation for Neural Machine Translationcited by 242
  9. 2019ERNIE 2.0: A Continual Pre-training Framework for Language Understandingcited by 231
  10. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
  11. 2019Assessing BERT's Syntactic Abilitiescited by 192
  12. 2018Chinese NER Using Lattice LSTMcited by 81
12 more
  1. 2020FLAT: Chinese NER Using Flat-Lattice Transformercited by 67
  2. 2019Glyce: Glyph-vectors for Chinese Character Representationscited by 46
  3. 2019ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representationscited by 35
  4. 2019Simplify the Usage of Lexicon in Chinese NERcited by 23
  5. 2017Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRFcited by 16
  6. 2017Neural Word Segmentation with Rich Pretrainingcited by 10
  7. 2018State-of-the-art Chinese Word Segmentation with Bi-LSTMscited by 10
  8. 2018Subword Encoding in Lattice LSTM for Chinese Word Segmentationcited by 7
  9. 2019CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognitioncited by 5
  10. 2017Combining Discrete and Neural Features for Sequence Labelingcited by 4
  11. 2019BERT Meets Chinese Word Segmentationcited by 4
  12. 2019Investigating Self-Attention Network for Chinese Word Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 15; 2023: 6; 2024: 5; 2025: 4; 2026: 1.

34 papers.

Sort:

By area:

  1. 2022A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasetscited by 45
  2. 2022METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweetscited by 12
  3. 2022LERT: A Linguistically-motivated Pre-trained Language Modelcited by 11
  4. 2022PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasetscited by 10
  5. 2025XRAG: Cross-lingual Retrieval-Augmented Generationcited by 9
  6. 2022Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognitioncited by 7
  7. 2024PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognitioncited by 6
  8. 2024Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challengescited by 5
  9. 2022TURNER: The Uncertainty-based Retrieval Framework for Chinese NERcited by 4
  10. 2024TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilitiescited by 4
  11. 2021Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledgecited by 3
  12. 2022Robust Self-Augmentation for Named Entity Recognition with Meta Reweightingcited by 3
22 more
  1. 2022Chinese Word Segmentation with Heterogeneous Graph Neural Networkcited by 2
  2. 2022Qtrade AI at SemEval-2022 Task 11: An Unified Framework for Multilingual NER Taskcited by 2
  3. 2022Structural Bias for Aspect Sentiment Triplet Extractioncited by 2
  4. 2022YATO: Yet Another deep learning based Text analysis Open toolkitcited by 2
  5. 2022Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labelingcited by 2
  6. 2023Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfercited by 2
  7. 2025Joint Modeling of Entities and Discourse Relations for Coherence Assessmentcited by 2
  8. 2023Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCNcited by 1
  9. 2023Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanismcited by 1
  10. 2024An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labelingcited by 1
  11. 2021Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Applicationcited by 0
  12. 2021Few-shot Multi-hop Question Answering over Knowledge Basecited by 0
  13. 2022NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognitioncited by 0
  14. 2022Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speechcited by 0
  15. 2022Exploiting Word Semantics to Enrich Character Representations of Chinese Pre-trained Modelscited by 0
  16. 2023Unified Model Learning for Various Neural Machine Translationcited by 0
  17. 2023KESDT: knowledge enhanced shallow and deep Transformer for detecting adverse drug reactionscited by 0
  18. 2023Unified Lattice Graph Fusion for Chinese Named Entity Recognitioncited by 0
  19. 2024Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-trainingcited by 0
  20. 2025Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanationscited by 0
  21. 2025A RoBERTa-Based Functional Syntax Annotation Model for Chinese Textscited by 0
  22. 2026ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detectioncited by 0