Automatic hypertext keyphrase detection

Daniel Kelleher, Saturnino F. Luz · International Joint Conference on Artificial Intelligence · 2005

This paper describes initial experiments in applying knowledge derived from hypertext structure to domain-specific automatic keyphrase extraction. It is found that hyperlink information can improve the effectiveness of automatic keyphrase extraction by 50%. However, the primary goal of this project is to apply similar techniques to information retrieval tasks such as web searching. These initial results show promise for the applicability of these techniques to more far-reaching tasks.

Read the paper · More papers on PaperTik