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.

Scaling Adversarial Cross-Lingual NER Models with Multilingual Embeddings for Zero-Shot Domain Accuracy in Low-Resource Languages

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: What is the effect of scaling adversarial cross-lingual NER models with larger multilingual embeddings (e.g., mT5 vs. XLM-R) on zero-shot cross-domain entity recognition accuracy across low-resource languages, as measured on domain-specific datasets like ECCO or MUSEE? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.1/10.

Visit

doi.org

Tasks

information extractionnamed entity recognitiontransfer learning

Tags

effectscalingadversarialcross-lingualNERmodelslargermultilingual

Licenses

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

Similaires

Projection-based Cross-lingual NER vs. Zero-shot Multilingual Models in Low-resource LanguagesMultilingual Adversarial Training for Robust Zero-Shot Cross-Lingual Transfer in Low-Resource LanguagesParameter Scaling in Encoder-Only Models for Zero-Shot Cross-Lingual Accuracy on XTREME-R Low-Resource LanguagesCross-lingual STS Method vs Multilingual Language Models in Zero-shot Low-resource AccuracyHybrid Batch Training vs. Adversarial Domain Adaptation in Zero-Shot Cross-Lingual Retrieval for Low-Resource LanguagesMultimodal vs. Text-Only Models in Zero-Shot Cross-Lingual NER for Low-Resource Languages

Projection-based Cross-lingual NER vs. Zero-shot Multilingual Models in Low-resource Languages

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

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

Parameter Scaling in Encoder-Only Models for Zero-Shot Cross-Lingual Accuracy on XTREME-R Low-Resource Languages

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Cross-lingual STS Method vs Multilingual Language Models in Zero-shot Low-resource Accuracy

Pretrained multilingual language models have become a common tool in transferring NLP capabilities t

Hybrid Batch Training vs. Adversarial Domain Adaptation in Zero-Shot Cross-Lingual Retrieval for Low-Resource Languages

Information retrieval across different languages is an increasingly important challenge in natural l

Multimodal vs. Text-Only Models in Zero-Shot Cross-Lingual NER for Low-Resource Languages

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