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.

Continuing Pre-training on Low-Resource African Corpora for Zero-Shot XNLI Transfer Accuracy

Domaine:

natural language processing
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (MultiHowTo100M) for pre-training. Experimen Research goal: How does continuing pre-training on low-resource African language corpora affect zero-shot cross-lingual transfer accuracy on the XNLI benchmark compared to standard multilingual baselines? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 9.3/10.

Visit

doi.orgzenodo.org

Tags

continuingpre-traininglow-resourceAfricanlanguagecorporaaffectzero-shot

Licenses

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

Similaires

Intermediate-Task Training on English NLI for Zero-Shot XCOPA and XNLI Accuracy in Low-Resource LanguagesContrastive Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer in Low-Resource LanguagesImpact of Monolingual-Crosslingual Data Ratios on Zero-Shot Retrieval Accuracy in Low-Resource XNLIImpact of Multilingual Intermediate-Task Training on Zero-Shot Cross-Lingual Transfer Accuracy in XTREME-R for Low-ResourceIntermediate-Task Training for Low-Resource Zero-Shot Cross-Lingual TransferZero-shot Cross-lingual Transfer Accuracy in Multilingual vs. English Intermediate-Task Training for Low-Resource Languages

Intermediate-Task Training on English NLI for Zero-Shot XCOPA and XNLI Accuracy in Low-Resource Languages

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

Contrastive Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer in Low-Resource Languages

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focu

Impact of Monolingual-Crosslingual Data Ratios on Zero-Shot Retrieval Accuracy in Low-Resource XNLI

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

Impact of Multilingual Intermediate-Task Training on Zero-Shot Cross-Lingual Transfer Accuracy in XTREME-R for Low-Resource

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

Intermediate-Task Training for Low-Resource Zero-Shot Cross-Lingual Transfer

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

Zero-shot Cross-lingual Transfer Accuracy in Multilingual vs. English Intermediate-Task Training for Low-Resource Languages

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