We present HyperSum, an extractive summarization framework that captures both
the efficiency of traditional lexical summarization and the accuracy of
contemporary neural approaches. HyperSum exploits the pseudo-orthogonality that
emerges when randomly initializing vectors at extremely high dimensions
("blessing of dimensionality") to construct representative and efficient
sentence embeddings. Simply clustering the obtained embeddings and extracting
their medoids yields competitive summaries. HyperSum often outperforms
state-of-the-art summarizers -- in terms of both summary accuracy and
faithfulness -- while being 10 to 100 times faster. We open-source HyperSum as
a strong baseline for unsupervised extractive summarization.

HyperSum 是一种提取式摘要框架，能够结合传统词汇摘要的效率和现代神经网络方法的准确性，通过利用在极高维度 (“维度祝福”) 上对向量进行随机初始化时出现的伪正交现象来构建具有代表性和高效的句子嵌入。通过简单地聚类所获取的嵌入并提取它们的中心，可以得到有竞争力的摘要。HyperSum 在摘要的准确性和可信度方面往往优于最先进的摘要器，同时速度快 10 至 100 倍。我们将 HyperSum 开源作为无监督的提取式摘要的强基准。