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.

Cross-lingual Query Generation Effects on Dense Retrieval Robustness in Low-Resource XQuAD Subsets

Domain:

natural language processing
Creator:
Ass
Publisher:
Zenodo
Host:avatar
Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data for training is often scarcely available. In this paper, rather than using more cross-lingual data for training, we propose to use cross-lingual query generation to augment passage representations with queries in languages other than the original passage language. These augmented representations are used at inference time so that the representation can enco Research goal: How does cross-lingual query generation impact the robustness of dense retrieval models on low-resource language subsets of XQuAD compared to standard multilingual fine-tuning? 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 retrievaltransfer learning

Tags

cross-lingualquerygenerationimpactrobustnessdenseretrievalmodels

Licenses

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

Similar

Query Augmentation for Cross-Lingual Dense Retrieval in Low-Resource LanguagesCross-Lingual Query Generation Augmentation for Robust Dense Retrieval Against Adversarial Paraphrases in Low-Resource LanguagesQuery-Augmented vs. Passage-Augmented Cross-Lingual Dense Retrieval on Low-Resource MTrQAFine-Tuning Dense Retrievers on WebFAQ Low-Resource Subsets for Zero-Shot Cross-Lingual XQuAD AccuracyMonolingual-to-Cross-Lingual Batch Ratio Effects on Zero-Shot Retrieval Robustness in XQuAD Low-Resource LanguagesSynthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource Languages

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

Cross-Lingual Query Generation Augmentation for Robust Dense Retrieval Against Adversarial Paraphrases in Low-Resource Languages

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

Query-Augmented vs. Passage-Augmented Cross-Lingual Dense Retrieval on Low-Resource MTrQA

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

Fine-Tuning Dense Retrievers on WebFAQ Low-Resource Subsets for Zero-Shot Cross-Lingual XQuAD Accuracy

We present WebFAQ, a large-scale collection of open-domain question answering datasets derived from

Monolingual-to-Cross-Lingual Batch Ratio Effects on Zero-Shot Retrieval Robustness in XQuAD Low-Resource Languages

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

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