Synthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource Languages
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
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: To what extent does synthetic query augmentation improve zero-shot cross-lingual dense retrieval performance on low-resource language pairs within the XNLI benchmark compared to high-resource pairs?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.7/10.
Similar
Synthetic Cross-Lingual Query Volume and Zero-Shot Dense Retrieval Accuracy in XNLI Low-Resource LanguagesQuery Augmentation for Cross-Lingual Dense Retrieval in Low-Resource LanguagesCross-Lingual Query Generation Augmentation for Robust Dense Retrieval Against Adversarial Paraphrases in Low-Resource LanguagesZero-shot Cross-lingual Retrieval Generalization to Low-Resource LanguagesBilingual Lexicons for Zero-Shot Cross-Lingual Retrieval in Low-Resource LanguagesZero-shot Cross-lingual Retrieval Accuracy Degradation in Low-Resource Languages