最小监督下的时间常识习得
Temporal Common Sense Acquisition with Minimal Supervision
摘要：
时间常识（例如，事件的持续时间和频率）对于理解自然语言至关重要。然而，它的获取是具有挑战性的，部分原因是这些信息往往没有明确地表达在文本中，并且人类对这些概念的注释是昂贵的。这项工作提出了一种新的序列建模方法，利用显式和隐式提到的时间常识，从一个大型语料库中提取，建立TACOLM，时间常识语言模型。我们的方法被证明是给质量预测的各种维度的时间常识（UDST和一个新收集的数据集从RealNews）。它还产生表示的相关任务，如持续时间比较，父子关系，事件相互引用和时间QA（在TimeBank，HiEVE和MCTACO），比使用标准的BERT更好。因此，它将是时态NLP的重要组成部分。
英文摘要：
Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on such concepts is costly. This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TACOLM, a temporal common sense language model. Our method is shown to give quality predictions of various dimensions of temporal common sense (on UDST and a newly collected dataset from RealNews). It also produces representations of events for relevant tasks such as duration comparison, parent-child relations, event coreference and temporal QA (on TimeBank, HiEVE and MCTACO) that are better than using the standard BERT. Thus, it will be an important component of temporal NLP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
