Recent work on unsupervised question answering has shown that models can be trained with procedurally generated question-answer pairs and can achieve performance competitive with supervised methods. In this work, we consider the task of unsupervised reading comprehension and present a method that performs "test-time learning" (TTL) on a given context (text passage), without requiring training on large-scale human-authored datasets containing \textit{context-question-answer} triplets. This method operates directly on a single test context, uses self-supervision to train models on synthetically generated question-answer pairs, and then infers answers to unseen human-authored questions for this context. Our method achieves accuracies competitive with fully supervised methods and significantly outperforms current unsupervised methods. TTL methods with a smaller model are also competitive with the current state-of-the-art in unsupervised reading comprehension.
翻译:在这项工作中,我们考虑了不受监督的阅读理解任务,并提出了一种在特定背景下(文本通过)进行“测试学习”的方法(TTL),而不需要对包含\ textit{context- question} 3⁄4的大型人类授权数据集进行培训。这个方法直接在单一测试背景下运作,使用自我监督的观察来培训合成生成的问答对等模型,然后为这一背景下的未知的人源问题解答解出答案。我们的方法在完全监督的方法下实现了“测试学习”的竞争性,大大超越了目前不受监督的方法。具有较小模型的TTL方法也与目前不受监督的阅读理解中的最新技术具有竞争力。