Using and Evaluating User Directed Summaries to Improve Information Access

摘要: Textual information available has grown so much as to make necessary study new techniques that assist users in access (IA). In this paper, we propose utilizing a user directed summarization system an IA setting for helping decide about document relevance. The summaries are generated using sentence extraction method scores the sentences performing some heuristics employed successfully previous works (keywords, title and location). User modeling is carried out exploiting user's query expanding terms WordNet. We present objective systematic evaluation oriented measure summary effectiveness two significant tasks: ad hoc retrieval relevance feedback. Results obtained prove our initial hypothesis, i.e., adapted useful tool assisting context.