High-Precision Extraction of Emerging Concepts from Scientific Literature

TL;DR

This paper introduces an unsupervised method for extracting emerging scientific concepts with high precision by identifying influential papers that introduce or popularize these concepts, significantly outperforming previous techniques.

Contribution

The authors propose a novel unsupervised approach that leverages citation patterns to accurately identify new scientific concepts, achieving higher precision than existing methods.

Findings

Precision@1000 of 99% for the proposed method

Outperforms prior work with 86% Precision@1000

Provides code and data for further research

Abstract

Identification of new concepts in scientific literature can help power faceted search, scientific trend analysis, knowledge-base construction, and more, but current methods are lacking. Manual identification cannot keep up with the torrent of new publications, while the precision of existing automatic techniques is too low for many applications. We present an unsupervised concept extraction method for scientific literature that achieves much higher precision than previous work. Our approach relies on a simple but novel intuition: each scientific concept is likely to be introduced or popularized by a single paper that is disproportionately cited by subsequent papers mentioning the concept. From a corpus of computer science papers on arXiv, we find that our method achieves a Precision@1000 of 99%, compared to 86% for prior work, and a substantially better precision-yield trade-off across the top 15,000 extractions. To stimulate research in this area, we release our code and data (https://github.com/allenai/ForeCite).