The original version of this story appeared in Quanta Magazine. Sometime in the fall of 2021, Andrew Krapivin, an undergraduate at Rutgers University, encountered a paper that would change his life. At the time, Krapivin didn't give it much thought. But two years later, when he finally set aside time to go through the paper ("just for fun," as he put it), his efforts would lead to a rethinking of a widely used tool in computer science. The paper's title, "Tiny Pointers," referred to arrowlike entities that can direct you to a piece of information, or element, in a computer's memory. Krapivin soon came up with a potential way to further miniaturize the pointers so they consumed less memory.

Keyphrases are phrases in a document providing a concise summary of core content, helping readers to understand what the article is talking about in a minute. However, existing unsupervised works are not robust enough to handle various types of documents owing to the mismatch of sequence length for comparison. In this paper, we propose a novel unsupervised keyword extraction method by leveraging the BERT-based model to select and rank candidate keyphrases with a MASK strategy. In addition, we further enhance the model, denoted as Keyphrases Extraction BERT (KPEBERT), via designing a compatible self-supervised task and conducting a contrast learning. We conducted extensive experimental evaluation to demonstrate the superiority and robustness of the proposed method as well as the effectiveness of KPEBERT.