Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Improving Cross-Lingual NER Robustness via Contrastive Learning in XTREME-R

Domain:

natural language processing

Record type:

paper
Creator:
Ass
Publisher:
Zenodo
Host: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 the robustness of cross-lingual NER models be further improved by incorporating contrastive learning techniques, and how does this impact accuracy on low-resource languages in XTREME-R? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.7/10.

Visit

doi.org

Tasks

information extractionnamed entity recognitiontransfer learning

Tags

robustnesscross-lingualNERmodelsfurtherimprovedincorporatingcontrastive

Licenses

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

Similar

Cross-lingual NER Robustness with Variable Source Language Counts in XTREME-NERCross-lingual NER performance variation in XTREME-R low-resource languages via annotation projectionRobustness of Cross-Lingual NER Models in Low-Resource Languages via Teacher-Student LearningContrastive Learning with Synthetic Cross-Lingual Pairs for Zero-Shot Transfer on XTREME-RRobustness in Zero-Shot Cross-Lingual Transfer via Intermediate-Task Training for Low-Resource Languages in XTREME-RAdversarial Training Impact on Zero-Shot Cross-Lingual Robustness in XTREME-R

Cross-lingual NER Robustness with Variable Source Language Counts in XTREME-NER

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

Cross-lingual NER performance variation in XTREME-R low-resource languages via annotation projection

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

Robustness of Cross-Lingual NER Models in Low-Resource Languages via Teacher-Student Learning

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

Contrastive Learning with Synthetic Cross-Lingual Pairs for Zero-Shot Transfer on XTREME-R

Recently, although pre-trained language models have achieved great success on multilingual NLP (Natu

Robustness in Zero-Shot Cross-Lingual Transfer via Intermediate-Task Training for Low-Resource Languages in XTREME-R

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

Adversarial Training Impact on Zero-Shot Cross-Lingual Robustness in XTREME-R

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