Impact of Code-Switched Token Proportions on Zero-Shot Cross-Lingual Retrieval Robustness

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 varying the proportion of code-switched tokens in training data affect the robustness of zero-shot cross-lingual retrieval models when evaluated on adversarial multilingual inputs, as measured by accuracy degradation on BEIR benchmarks with perturbed queries?

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