Ask Me Anything in Your Native Language
Nikita Sorokin, Dmitry Abulkhanov, Irina Piontkovskaya, Valentin Malykh
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%.
BibTeX
@inproceedings{sorokin-etal-2022-ask,
title = "Ask Me Anything in Your Native Language",
author = "Sorokin, Nikita and
Abulkhanov, Dmitry and
Piontkovskaya, Irina and
Malykh, Valentin",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.30/",
doi = "10.18653/v1/2022.naacl-main.30",
pages = "395--406"
}