A Comparison of Centrality Measures for Graph-Based Keyphrase Extraction
Abstract
In this paper, we present and compare various centrality measures for graph-based keyphrase extraction. Through experiments carried out on three standard datasets of different languages and domains, we show that simple degree centrality achieve results comparable to the widely used TextRank algorithm, and that closeness centrality obtains the best results on short documents.
Domains
Document and Text Processing
Origin : Files produced by the author(s)
Loading...