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.

Synthetic Cross-Lingual Query Volume and Zero-Shot Dense Retrieval Accuracy in XNLI Low-Resource Languages

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Multilingual Pretrained Language Models (MPLMs) perform strongly in cross-lingual transfer. We propose Prompts Augmented by Retrieval Crosslingually (PARC) to improve zero-shot performance on low-resource languages (LRLs) by augmenting the context with prompts consisting of semantically similar sentences retrieved from a high-resource language (HRL). PARC improves zero-shot performance on three downstream tasks (sentiment classification, topic categorization, natural language inference) with multilingual parallel test sets across 10 LRLs covering 6 language families in unlabeled (+5.1\%) and la Research goal: How does the volume of synthetically generated cross-lingual queries impact the zero-shot accuracy of dense retrieval models on the XNLI benchmark for low-resource languages? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.5/10.

Visit

doi.orgzenodo.org

Tags

volumesyntheticallygeneratedcross-lingualqueriesimpactzero-shotaccuracy

Licenses

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

Similaires

Synthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource LanguagesZero-shot Cross-lingual Retrieval Accuracy Degradation in Low-Resource LanguagesQuery Augmentation for Cross-Lingual Dense Retrieval in Low-Resource LanguagesHybrid Batch Training Effects on Zero-Shot Cross-Lingual Retrieval Accuracy in Low-Resource LanguagesHybrid Batch Training Impact on Zero-Shot Cross-Lingual Retrieval Accuracy in Low-Resource LanguagesDiversity in Training Languages for Dense Retrieval and Zero-Shot Accuracy in Low-Resource Benchmarks

Synthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource Languages

Multilingual Pretrained Language Models (MPLMs) perform strongly in cross-lingual transfer. We propo

Zero-shot Cross-lingual Retrieval Accuracy Degradation in Low-Resource Languages

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

Query Augmentation for Cross-Lingual Dense Retrieval in Low-Resource Languages

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language model

Hybrid Batch Training Effects on Zero-Shot Cross-Lingual Retrieval Accuracy in Low-Resource Languages

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

Hybrid Batch Training Impact on Zero-Shot Cross-Lingual Retrieval Accuracy in Low-Resource Languages

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

Diversity in Training Languages for Dense Retrieval and Zero-Shot Accuracy in Low-Resource Benchmarks

Accuracy of English-language Question Answering (QA) systems has improved significantly in recent ye