Searching for a specific and meaningful piece of information in the humongous textual data volumes found on the internet and knowledge repositories is a very challenging task. This problem is usually constrained to answering simple, factoid questions by resorting to a question answering (QA) system built on top of complex approaches such as heuristics, information retrieval, and machine learning. More precisely, deep learning methods became into sharp focus of this research field because such purposes can realize the benefits of the vast amounts of data to boost the practical results of QA systems. In this paper, we present a systematic survey on deep learning-based QA systems concerning factoid questions, with particular focus on how each existing system addresses their critical features in terms of learning end-to-end models. We also detail the evaluation process carried out on these systems and discuss how each approach differs from the others in terms of the challenges tackled and the strategies employed. Finally, we present the most prominent research problems still open in the field.

中文翻译：

---

关于端到端简单问答系统的简短调查

在互联网和知识库中发现的大量文本数据中搜索特定且有意义的信息是一项非常具有挑战性的任务。这个问题通常被限制在通过求助于建立在复杂方法（如启发式、信息检索和机器学习）之上的问答 (QA) 系统来回答简单的、事实性的问题。更准确地说，深度学习方法成为该研究领域的重点，因为这样的目的可以实现海量数据的好处，从而提升 QA 系统的实际结果。在本文中，我们对基于深度学习的 QA 系统进行了系统调查，涉及事实类问题，特别关注每个现有系统如何在学习端到端模型方面解决其关键特征。我们还详细介绍了对这些系统进行的评估过程，并讨论了每种方法在应对的挑战和采用的策略方面与其他方法有何不同。最后，我们提出了该领域仍然存在的最突出的研究问题。