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.

Gradient Clipping Thresholds in XLM-R Fine-Tuning for Zero-Shot Cross-Lingual Transfer

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contex Research goal: What is the impact of gradient clipping thresholds during fine-tuning on the zero-shot cross-lingual transfer performance of XLM-R Base, and how do different thresholds compare in terms of downstream task accuracy on XTREME-R? 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

transfer learning

Tags

impactgradientclippingthresholdsduringfine-tuningzero-shotcross-lingual

Licenses

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

Similaires

Gradient-based adversarial fine-tuning for XLM-R robustness in zero-shot cross-lingual classificationContrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-RContrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-TuningSequential Fine-Tuning Task Quantity and Zero-Shot Cross-Lingual Transfer in XTREME-RHybrid Batch Training for XLM-R in Zero-Shot Cross-Lingual TransferMultimodal Alignment Tasks and Zero-Shot Cross-Lingual Transfer in XLM-R

Gradient-based adversarial fine-tuning for XLM-R robustness in zero-shot cross-lingual classification

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

Contrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-R

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

Contrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-Tuning

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec

Sequential Fine-Tuning Task Quantity and Zero-Shot Cross-Lingual Transfer in XTREME-R

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec

Hybrid Batch Training for XLM-R in Zero-Shot Cross-Lingual Transfer

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

Multimodal Alignment Tasks and Zero-Shot Cross-Lingual Transfer in XLM-R

The introduction of pretrained cross-lingual language models brought decisive improvements to multil