Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Adversarial Training for Robust Cross-Lingual NER in Low-Resource Settings

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to identify and classify named entities, making it particularly useful for low-resource languages. We show that the data-based cross-lingual transfer method is an effective technique for crosslingual NER and can outperform multilingual language models for low-resource languages. This paper introduces two key enhancements to the annotation projection step in cross-lingual NER for low-resource languages. First, we explore refining word alignments using back-translation to improve accuracy. Second, we pres Research goal: Can adversarial training during the projection-based data transfer step improve the robustness of cross-lingual NER models against distribution shifts in low-resource language datasets, as evaluated by accuracy on the MLQA benchmark? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.

Visit

doi.org

Tasks

information extractionnamed entity recognitiontransfer learning

Tags

adversarialtrainingduringprojection-baseddatatransferstepimprove

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Adversarial Training for Robust Cross-Lingual Retrieval in Low-Resource SettingsMultilingual Adversarial Training for Robust Zero-Shot Cross-Lingual Transfer in Low-Resource LanguagesProjection-based Data Augmentation and Adversarial Training for Robust Low-resource NERMultimodal Alignment for Robust Cross-Lingual NER in Low-Resource LanguagesScaling Out-of-Domain Unlabeled Data for Robust Cross-Lingual NER Alignment in Low-Resource SettingsArtificially Code-Switched Training Data for Robust Zero-Shot Cross-Lingual Ranking in Low-Resource Settings

Adversarial Training for Robust Cross-Lingual Retrieval in Low-Resource Settings

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Multilingual Adversarial Training for Robust Zero-Shot Cross-Lingual Transfer in Low-Resource Languages

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Projection-based Data Augmentation and Adversarial Training for Robust Low-resource NER

Named Entity Recognition(NER) for low-resource languages aims to produce robust systems for language

Multimodal Alignment for Robust Cross-Lingual NER in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Scaling Out-of-Domain Unlabeled Data for Robust Cross-Lingual NER Alignment in Low-Resource Settings

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Artificially Code-Switched Training Data for Robust Zero-Shot Cross-Lingual Ranking in Low-Resource Settings

Transferring information retrieval (IR) models from a high-resource language (typically English) to