Ask Me Anything in Your Native Language

Abstract

Cross-lingual question answering is a thriving field in the modern world, helping people to search information on the web more efficiently. One of the important scenarios is to give an answer even there is no answer in the language a person asks a question with. We present a novel approach to achieving a new state of the art in both retrieval and end-to-end tasks on the XOR TyDi dataset outperforming the previous results up to 10\% on several languages. We find that our approach can be generalized to more than 100 languages in zero-shot approach and outperform all previous models by 8\%.

Tasks

Reproductions