mlsanityData to 14 Oct 2026

ConNER: Consistency Training for Cross-lingual Named Entity Recognition

arXiv 2211.09394 ↗First posted 17 Nov 2022cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Cross-lingual named entity recognition (NER) suffers from data scarcity in the target languages, especially under zero-shot settings. Existing translate-train or knowledge distillation methods attempt to bridge the language gap, but often introduce a high level of noise. To solve this problem, consistency training methods regularize the model to be robust towards perturbations on data or hidden states. However, such methods are likely to violate the consistency hypothesis, or mainly focus on coarse-grain consistency. We propose ConNER as a novel consistency training framework for cross-lingual NER, which comprises of: (1) translation-based consistency training on unlabeled target-language data, and (2) dropoutbased consistency training on labeled source-language data. ConNER effectively leverages unlabeled target-language data and alleviates overfitting on the source language to enhance the cross-lingual adaptability. Experimental results show our ConNER achieves consistent improvement over various baseline methods.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

24 of 40 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  4. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  5. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  6. 2016Neural Architectures for Named Entity Recognitioncited by 550
  7. 2021R-Drop: Regularized Dropout for Neural Networkscited by 202
  8. 2018Semi-Supervised Sequence Modeling with Cross-View Trainingcited by 75
  9. 2018Neural Cross-Lingual Named Entity Recognition with Minimal Resourcescited by 44
  10. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  11. 2021Consistency Regularization for Cross-Lingual Fine-Tuningcited by 41
  12. 2020Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Languagecited by 37
12 more
  1. 2019Entity Projection via Machine Translation for Cross-Lingual NERcited by 32
  2. 2020UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Datacited by 24
  3. 2020Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyondcited by 22
  4. 2021Better Feature Integration for Named Entity Recognitioncited by 22
  5. 2019Zero-Resource Cross-Lingual Named Entity Recognitioncited by 18
  6. 2021AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NERcited by 17
  7. 2021Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognitioncited by 15
  8. 2021Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triplescited by 13
  9. 2020Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Datacited by 11
  10. 2022PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Taskscited by 7
  11. 2021Target-Oriented Fine-tuning for Zero-Resource Named Entity Recognitioncited by 5
  12. 2021Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddingscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 9.

11 papers.

  1. 2022Frustratingly Easy Label Projection for Cross-lingual Transfercited by 33
  2. 2022T-Projection: High Quality Annotation Projection for Sequence Labeling Taskscited by 14
  3. 2023mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learningcited by 14
  4. 2023Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learningcited by 8
  5. 2023Easy-to-Hard Learning for Information Extractioncited by 5
  6. 2023MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extractioncited by 3
  7. 2023mPMR: A Multilingual Pre-trained Machine Reader at Scalecited by 2
  8. 2023CebuaNER: A New Baseline Cebuano Named Entity Recognition Modelcited by 2
  9. 2023CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognitioncited by 1
  10. 2023Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languagescited by 0
  11. 2023Cross-Lingual NER for Financial Transaction Data in Low-Resource Languagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022A Dual-Contrastive Framework for Low-Resource Cross-Lingual Named Entity Recognition
  2. 2023ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition
  3. 2025Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective
  4. 2025FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition
  5. 2021CL-NERIL: A Cross-Lingual Model for NER in Indian Languages
  6. 2022WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition
  7. 2023Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models
  8. 2023DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition