Story Link Detection with Entity Resolution
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
News archives present a vast base of cultural and social knowledge. However, their size is also the cause for difficult navigation through the sequence of articles, belonging to a certain topic thread. In the ideal scenario, one could navigate over the whole sequence of articles, where every article would link to other relevant articles, discussing the same event. Continuing progress in entity resolution and extraction has enabled the possibility to apply semantic background knowledge to the task of story link detection (SLD), adding additional information to existing article text and annotations. In this paper, we propose a method of extracted entity resolution to measure its effect on performance the task of topic link detection. We developed a system which extracts additional entities from article text and links them to entities from our background knowledge base. Current experiments of this ongoing work show that although entity resolution via text similarity outperforms using plain text in the case of story link detection, it only achieves SLD performance comparable to human annotations in some cases.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !