Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

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

Domain:

natural language processing

Record type:

paper
Creator:
Ass
Publisher:
Zenodo
Host: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: How does the scaling of zero-shot cross-lingual retrieval models trained on code-switched data impact retrieval performance in low-resource languages, as measured by MRR@10 scores across different model sizes (small, medium, large)? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.6/10.

Visit

doi.orgzenodo.org

Tasks

code switchinginformation retrieval

Tags

scalingzero-shotcross-lingualretrievalmodelstrainedcode-switcheddata

Licenses

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

Similar

Performance of Zero-Shot Cross-Lingual Retrieval Models Trained on Artificial Code-Switched Data on Unseen Low-Resource LanguagesScaling Model Size for Zero-Shot Cross-Lingual Retrieval on Code-Switched Data in Low-Resource LanguagesGeneralization of Cross-Lingual Retrieval Models Trained on Code-Switched Data to Low-Resource LanguagesCross-Lingual Embeddings for Zero-Shot Retrieval on Artificially Code-Switched Low-Resource DataScaling Bilingual Lexicons for Zero-Shot Cross-Lingual Retrieval on Artificially Code-Switched Low-Resource Data in MIRACLPerformance of Zero-Shot Cross-Lingual Retrieval Models on Low-Resource Languages with Adversarial Code-Switched Training

Performance of Zero-Shot Cross-Lingual Retrieval Models Trained on Artificial Code-Switched Data on Unseen Low-Resource Languages

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

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

Generalization of Cross-Lingual Retrieval Models Trained on Code-Switched Data to Low-Resource Languages

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

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

Scaling Bilingual Lexicons for Zero-Shot Cross-Lingual Retrieval on Artificially Code-Switched Low-Resource Data in MIRACL

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

Performance of Zero-Shot Cross-Lingual Retrieval Models on Low-Resource Languages with Adversarial Code-Switched Training

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