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.

ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters | VIDEO

Domaine:

natural language processing

Type de record:

paper
Créateur:
AssMauDhiRat
Éditeur:
Und
Hôte:avatar
We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the target LA or LA of another related language. Training target LA requires unlabeled data, which may not be readily available for low resource unseen languages: those that are neither seen by the underlying multilingual language model (e.g., mBERT), nor do we have any (labeled or unlabeled) data for them. We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL. Extensive experimentation across four language groups, covering 15 unseen target languages, demonstrates improvements of up to 3.2 average F1 points over standard fine-tuning and other strong baselines on POS tagging and NER tasks. We also extend ZGUL to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language. We find that ZGUL continues to outperform baselines in these settings too.

Visit

doi.orgunderline.io

Tasks

information extractionnamed entity recognitionpart of speech taggingtransfer learning

Tags

Computational LinguisticsArtificial Intelligence

Similaires

Zero-shot Cross-lingual Retrieval Generalization to Low-Resource LanguagesOrthogonal Language and Task Adapters in Zero-Shot Cross-Lingual TransferImpact of Optimal Transport Distillation on Zero-Shot Cross-Lingual Retrieval for Unseen MIRACL LanguagesMulti-source Intermediate-task Training for Low-resource XTREME Language GeneralizationBAD-X: Bilingual Adapters Improve Zero-Shot Cross-Lingual TransferLinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization

Zero-shot Cross-lingual Retrieval Generalization to Low-Resource Languages

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

Orthogonal Language and Task Adapters in Zero-Shot Cross-Lingual Transfer

Adapter modules, additional trainable parameters that enable efficient fine-tuning of pretrained tra

Impact of Optimal Transport Distillation on Zero-Shot Cross-Lingual Retrieval for Unseen MIRACL Languages

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Multi-source Intermediate-task Training for Low-resource XTREME Language Generalization

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

BAD-X: Bilingual Adapters Improve Zero-Shot Cross-Lingual Transfer

Adapter modules enable modular and efficient zero-shot cross-lingual transfer, where current state-of-the-art adapter-based approaches learn specialized language adapters (LAs) for individual languages. In this work, we show that it is more effective to learn bilin

LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization

Pretrained language models (PLMs) have become remarkably adept at task and language generalization.