Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. Our first strategy augments the original English training data with machine translation-generated data. This results in a corpus of multilingual silver-labeled QA pairs that is 14 times larger than the original training set. In addition, we propose two novel strategies, language adversarial training and language arbitration framework, which significantly improve the (zero-resource) cross-lingual transfer performance and result in LM embeddings that are less language-variant. Empirically, we show that the proposed models outperform the previous zero-shot baseline on the recently introduced multilingual MLQA and TyDiQA datasets.

本文探索了提高多语言问题回答的交叉语言转移性能的策略，包括使用机器翻译生成的数据来增强原始英语训练数据，以及提出两种新颖的策略：语言对抗性训练和语言仲裁框架，这些策略显著提高了零资源的交叉语言转移性能，并导致 LM 嵌入不那么语言特定的结果。经验证明，这些模型在最近推出的 multilingual MLQA 和 TyDiQA 数据集上优于以前的零-shot基线。

使用翻译增强的多语言问答转移学习