Temporal question answering (QA) involves time constraints, with phrases such as "... in 2019" or "... before COVID". In the former, time is an explicit condition, in the latter it is implicit. State-of-the-art methods have limitations along three dimensions. First, with neural inference, time constraints are merely soft-matched, giving room to invalid or inexplicable answers. Second, questions with implicit time are poorly supported. Third, answers come from a single source: either a knowledge base (KB) or a text corpus. We propose a temporal QA system that addresses these shortcomings. First, it enforces temporal constraints for faithful answering with tangible evidence. Second, it properly handles implicit questions. Third, it operates over heterogeneous sources, covering KB, text and web tables in a unified manner. The method has three stages: (i) understanding the question and its temporal conditions, (ii) retrieving evidence from all sources, and (iii) faithfully answering the question. As implicit questions are sparse in prior benchmarks, we introduce a principled method for generating diverse questions. Experiments show superior performance over a suite of baselines.

翻译：时间问答（QA）涉及时间约束，例如“...于2019年”或“...COVID之前”等短语。前者中的时间是显式条件，后者则是隐式的。现有最先进的方法在三个维度上存在局限性。首先，在神经推理中，时间约束仅被软匹配，从而给无效或无法解释的答案留下空间。其次，对隐式时间问题的支持不足。第三，答案仅来源于单一来源：知识库（KB）或文本语料库。我们提出了一种时间问答系统，以解决这些缺陷。首先，该系统通过具体证据强制实施时间约束，实现忠实答案。其次，它妥善处理隐式问题。第三，它运行于异构源之上，以统一方式覆盖知识库、文本和网页表格。该方法包含三个步骤：（i）理解问题及其时间条件，（ii）从所有来源检索证据，以及（iii）忠实回答该问题。由于隐式问题在先前的基准中较为稀疏，我们引入了一种生成多样化问题的原则性方法。实验表明，该系统在一系列基线方法上具有更优性能。