Ask Me Anything in Your Native Language

Anonymous

Paper Link: https://openreview.net/forum?id=gcQjRKJx45I

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

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 based on single encoder for query and passage for retrieval from multi-lingual collection, together with cross-lingual generative reader. It achieves 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 20 languages in zero-shot approach and outperform all previous models by 12\%.

Presentation Mode: This paper will be presented in person in Seattle

Virtual Presentation Timezone: UTC+3

Copyright Consent Signature (type Name Or NA If Not Transferrable): Valentin Malykh

Copyright Consent Job Title: Senior Research Scientist

Copyright Consent Name And Address: Huawei Noah's Ark lab, Hong Kong