AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER

06/04/2021
by   Weile Chen, et al.
0

Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. While previous works have shown that unlabeled data in a target language can be used to improve cross-lingual model performance, we propose a novel adversarial approach (AdvPicker) to better leverage such data and further improve results. We design an adversarial learning framework in which an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarial training - where a discriminator selects less language-dependent target-language data via similarity to the source language. Experimental results on standard benchmark datasets well demonstrate that the proposed method benefits strongly from this data selection process and outperforms existing state-of-the-art methods; without requiring any additional external resources (e.g., gazetteers or via machine translation). The code is available at https://aka.ms/AdvPicker

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/26/2020

Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language

To better tackle the named entity recognition (NER) problem on languages...
research
07/15/2020

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...
research
05/24/2023

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

Cross-lingual named entity recognition (NER) aims to train an NER system...
research
06/01/2021

Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition

Named entity recognition (NER) is a fundamental component in many applic...
research
09/01/2021

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

Recent multilingual pre-trained language models have achieved remarkable...
research
08/13/2020

Adversarial Knowledge Transfer from Unlabeled Data

While machine learning approaches to visual recognition offer great prom...

Please sign up or login with your details

Forgot password? Click here to reset