Impact of Artificial Code-Switching Proportions on Zero-Shot Cross-Lingual Retrieval Robustness in Multilingual Legal Domains

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: What is the impact of varying the proportion of artificially code-switched tokens in training data on the robustness of zero-shot cross-lingual retrieval models, evaluated using recall and precision metrics on multilingual legal domain benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.