STRUCTURED TEXT REPRESENTATIONS AND RELEVANCE JUDGMENTS - AN EXPLORATORY-STUDY

This paper presents results of an exploratory study on using a structu red text and query model for analyzing relevance judgments made by use rs on retrieved texts 1The structured model moves beyond keyword based text representation and retrieval. In particular it allows texts and queries to be represented by concepts embedded within the structural f ramework of complex objects. These objects preserves important text-ba sed links between the selected concepts. The current study reveals a t endency for user judged relevance potential to decrease as the structu re-based similarity between query and text decreases. This indicates t hat the structure-based retrieval model has the potential to conduct m ore precise retrieval than keyword based models. This supports our ove rall research goal of developing and investigating the structured retr ieval model.