Cross-lingual question answering (CLQA) is a complex problem, comprising
cross-lingual retrieval from a multilingual knowledge base, followed by answer
generation either in English or the query language. Both steps are usually
tackled by separate models, requiring substantial annotated datasets, and
typically auxiliary resources, like machine translation systems to bridge
between languages. In this paper, we show that CLQA can be addressed using a
single encoder-decoder model. To effectively train this model, we propose a
self-supervised method based on exploiting the cross-lingual link structure
within Wikipedia. We demonstrate how linked Wikipedia pages can be used to
synthesise supervisory signals for cross-lingual retrieval, through a form of
cloze query, and generate more natural queries to supervise answer generation.
Together, we show our approach, \texttt{CLASS}, outperforms comparable methods
on both supervised and zero-shot language adaptation settings, including those
using machine translation.

基于自我监督方法的编码器 - 解码器模型在跨语言问答中表现出色，利用维基百科的跨语言链接结构，综合生成监督信号，提高了检索和回答生成的性能，相比于其他方法，包括机器翻译，CLASS 方法在监督和零资源语言适配等方面均取得更好的效果。