Understanding event descriptions is a central aspect of language processing,
but current approaches focus overwhelmingly on single sentences or documents.
Aggregating information about an event \emph{across documents} can offer a much
richer understanding. To this end, we present FAMuS, a new corpus of Wikipedia
passages that \emph{report} on some event, paired with underlying,
genre-diverse (non-Wikipedia) \emph{source} articles for the same event. Events
and (cross-sentence) arguments in both report and source are annotated against
FrameNet, providing broad coverage of different event types. We present results
on two key event understanding tasks enabled by FAMuS: \emph{source validation}
-- determining whether a document is a valid source for a target report event
-- and \emph{cross-document argument extraction} -- full-document argument
extraction for a target event from both its report and the correct source
article. We release both FAMuS and our models to support further research.

理解事件描述是语言处理的核心方面，但目前的方法主要集中在单个句子或文档上。跨文档汇总事件信息能提供更丰富的理解。为此，我们介绍了 FAMuS，这是一个新的维基百科段落语料库，用于报告某个事件，并提供与之对应的不同体裁（非维基百科）的源文章。我们对报告和源文章中的事件和跨句子的论证进行了 FrameNet 注释，提供了不同事件类型的广泛覆盖。我们展示了 FAMuS 支持的两个关键事件理解任务的结果：源验证 —— 确定一篇文档是否是目标报告事件的有效来源，以及跨文档的论证提取 —— 从报告和正确的源文章中提取目标事件的全文档论证。我们通过发布 FAMuS 和我们的模型来支持进一步研究。

FAMuS：多来源的帧

FAMuS: Frames Across Multiple Sources

It has been shown that deep neural networks are prone to overfitting on
biased training data. Towards addressing this issue, meta-learning employs a
meta model for correcting the training bias. Despite the promising
performances, super slow training is currently the bottleneck in the meta
learning approaches. In this paper, we introduce a novel Faster Meta Update
Strategy (FaMUS) to replace the most expensive step in the meta gradient
computation with a faster layer-wise approximation. We empirically find that
FaMUS yields not only a reasonably accurate but also a low-variance
approximation of the meta gradient. We conduct extensive experiments to verify
the proposed method on two tasks. We show our method is able to save two-thirds
of the training time while still maintaining the comparable or achieving even
better generalization performance. In particular, our method achieves the
state-of-the-art performance on both synthetic and realistic noisy labels, and
obtains promising performance on long-tailed recognition on standard
benchmarks.

本研究提出了一种 Faster Meta Update Strategy（FaMUS）来解决 meta-learning 中训练速度慢的问题，该方法能够在保持可比性或实现更好的泛化性能的同时，节省三分之二的训练时间，并在标准基准上实现了长尾识别的良好性能。