Scaling of Zero-Shot Cross-Lingual Retrieval with Bilingual Lexicon Size in Artificially Code-Switched Data on XQuAD

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 scale with the size of the bilingual lexicon used for data generation, as measured by accuracy on the XQuAD benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.