Zero-shot Cross-lingual Retrieval with Code-Switched vs. Back-Translated Data: XTREME-R Benchmark Analysis

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 zero-shot cross-lingual retrieval models trained on artificially code-switched data compare to models trained on back-translated data across different domains (e.g., Open Domain QA vs. Legal Domain QA) on the XTREME-R benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.