Performance of Multilingual Dense Retrievers on Code-Switched Data Across Cross-Lingual Benchmarks

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 performance of multilingual dense retrievers trained on artificially code-switched data vary across different cross-lingual benchmarks (e.g., MLIR, XTR), particularly for low-resource language pairs with varying degrees of linguistic divergence?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.