SALS-SIG Research Seminar

Automatically generating hypertext by computing semantic relatedness

Abstract:

I will be talking about a novel method for automatically generating hypertext links within and between newspaper articles. The method is based on lexical chaining, a technique for extracting the sets of related words that occur in texts.

In order to motivate the research, I'll discuss the results of a study that shows that humans are inconsistent when assigning hypertext links within newspaper articles. Even if humans were consistent, the time needed to build a large hypertext and the costs associated with the production of such a hypertext make relying on human linkers an untenable decision. Thus we are left to automatic hypertext generation.

Because I need to determine how our hypertext generation methodology performs when compared to other proposed methodologies, I'll describe a study comparing the hypertext linking methodology that I propose with a methodology based on a traditional information retreival approach. In this study, subjects were asked to perform a question-answering task using a combination of links generated by our methodology and the competing methodology. .

Enquiries: sals@mri.mq.edu.au