ConNER: Consistency Training for Cross-lingual Named Entity Recognition

by   Ran Zhou, et al.

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.


CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation

Named entity recognition (NER) suffers from the scarcity of annotated tr...

DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition

We present DualNER, a simple and effective framework to make full use of...

CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition

Cross-lingual named entity recognition (NER) aims to train an NER system...

Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation

Recent multilingual pre-trained language models have achieved remarkable...

Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition

Named entity recognition (NER) is a fundamental component in many applic...

MELM: Data Augmentation with Masked Entity Language Modeling for Cross-lingual NER

Data augmentation for cross-lingual NER requires fine-grained control ov...

UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data

Prior works in cross-lingual named entity recognition (NER) with no/litt...

Code Repositories


Repository for EMNLP 22 paper "ConNER: Consistency Training for Cross-lingual Named Entity Recognition"

view repo

Please sign up or login with your details

Forgot password? Click here to reset