Publication
Towards End-to-End Multilingual Question Answering
Ekaterina Loginova; Stalin Varanasi; Günter Neumann
In: Information Systems Frontiers (ISF), Vol. 22, Pages 1-14, Springer, 3/2020.
Abstract
Multilingual question answering (MLQA) is a critical part of an accessible natural language interface. However, current solutions
demonstrate performance far below that of monolingual systems.We believe that deep learning approaches are likely to improve
performance in MLQA drastically. This work aims to discuss the current state-of-the-art and remaining challenges. We outline
requirements and suggestions for practical parallel data collection and describe existing methods, benchmarks and datasets. We
also demonstrate that a simple translation of texts can be inadequate in case of Arabic, English and German languages (on
InsuranceQA and SemEval datasets), and thus more sophisticated models are required.We hope that our overview will re-ignite
interest in multilingual question answering, especially with regard to neural approaches.