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.

Degradation of Zero-Shot Cross-Lingual Retrieval on Code-Switched Data in Domain-Specific Low-Resource Language Pairs

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot rankers diminishes when queries and documents are present in different languages. Motivated by this, we propose to train ranking models on artificially code-switched data instead, which we generate by utilizing bilingual lexicons. To this end, we experiment with lexicons induced from (1) cross-lingual word embeddings and (2) parallel Wikipedia page titles. We use Research goal: To what extent does the effectiveness of zero-shot cross-lingual retrieval models trained on code-switched data degrade when evaluated on domain-specific low-resource language pairs (e.g., medical or legal texts) compared to general-domain language pairs, as measured by nDCG or MRR scores? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.8/10.

Visit

doi.orgzenodo.org

Tasks

information retrieval

Tags

extenteffectivenesszero-shotcross-lingualretrievalmodelstrainedcode-switched

Licenses

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

Similaires

Zero-shot Cross-lingual Retrieval Accuracy of XLM-R and mBART on Code-switched Low-resource Language PairsCross-Lingual Embeddings for Zero-Shot Retrieval on Artificially Code-Switched Low-Resource DataEffect of Domain-Specific Data on Zero-Shot Cross-Lingual Retrieval in Low-Resource LanguagesScaling Zero-Shot Cross-Lingual Retrieval Models Trained on Code-Switched Data for Low-Resource LanguagesZero-Shot Cross-Lingual Retrieval Robustness Under Varying Low-Resource Language Proportions in Code-Switched Training DataScaling Model Size for Zero-Shot Cross-Lingual Retrieval on Code-Switched Data in Low-Resource Languages

Zero-shot Cross-lingual Retrieval Accuracy of XLM-R and mBART on Code-switched Low-resource Language Pairs

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

Cross-Lingual Embeddings for Zero-Shot Retrieval on Artificially Code-Switched Low-Resource Data

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

Effect of Domain-Specific Data on Zero-Shot Cross-Lingual Retrieval in Low-Resource Languages

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

Scaling Zero-Shot Cross-Lingual Retrieval Models Trained on Code-Switched Data for Low-Resource Languages

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

Zero-Shot Cross-Lingual Retrieval Robustness Under Varying Low-Resource Language Proportions in Code-Switched Training Data

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

Scaling Model Size for Zero-Shot Cross-Lingual Retrieval on Code-Switched Data in Low-Resource Languages

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