Zero-shot cross-lingual retrieval effectiveness in low-resource languages with code-switched training

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 effectiveness of zero-shot cross-lingual retrieval scale when applied to low-resource languages (e.g., Swahili, Finnish) compared to high-resource languages, as measured by nDCG@10, when trained on code-switched data with varying ratios of source-target language pairs? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.2/10.