Unsupervised extraction of local and global keywords from a single text

TL;DR

This paper introduces an unsupervised, language-independent method for extracting local and global keywords from individual texts, improving effectiveness especially for long texts and uncovering thematic content.

Contribution

It presents a novel keyword extraction technique based on spatial word distribution and permutation response, capable of identifying local, global, and thematic keywords without supervision.

Findings

More effective for long texts compared to existing methods

Able to infer local and global keywords and basic themes

Supported by human annotation and linguistic analysis

Abstract

We propose an unsupervised, corpus-independent method to extract keywords from a single text. It is based on the spatial distribution of words and the response of this distribution to a random permutation of words. As compared to existing methods (such as e.g. YAKE) our method has three advantages. First, it is significantly more effective at extracting keywords from long texts. Second, it allows inference of two types of keywords: local and global. Third, it uncovers basic themes in texts. Additionally, our method is language-independent and applies to short texts. The results are obtained via human annotators with previous knowledge of texts from our database of classical literary works (the agreement between annotators is from moderate to substantial). Our results are supported via human-independent arguments based on the average length of extracted content words and on the average number of nouns in extracted words. We discuss relations of keywords with higher-order textual features and reveal a connection between keywords and chapter divisions.