Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages

Nie, Ercong; Liang, Sheng; Schmid, Helmut and Schütze, Hinrich (July 2023): Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages. 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), Toronto, Canada, July 2023. In: Findings of the Association for Computational Linguistics: ACL 2023, Stroudsburg, PA: Association for Computational Linguistics. pp. 8320-8340

Abstract

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 labeled settings (+16.3%). PARC also outperforms finetuning by 3.7%. We find a significant positive correlation between cross-lingual transfer performance on one side, and the similarity between high- and low-resource languages as well as the amount of low-resource pretraining data on the other side. A robustness analysis suggests that PARC has the potential to achieve even stronger performance with more powerful MPLMs.

• Item Type: Conference or Workshop Item (Paper)
• EU Funded Grant Agreement Number: 740516
• EU Projects: Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement
• Research Centers: Center for Information and Language Processing (CIS)
• Subjects: 400 Language > 400 Language; 400 Language > 410 Linguistics
• Place of Publication: Stroudsburg, PA
• Language: English