Our aim of participating in this year’s High Accuracy Retrieval from Documents (HARD) track is to explore the possibility of developing an automated HARD retrieval model by leve...
Abstract. The task of information extraction can be seen as a problem of semantic matching between a user-defined template and a piece of information written in natural language. T...
When investigating alternative estimates for term discriminativeness, we discovered that relevance information and idf are much closer related than formulated in classical literat...
Searching for small objects (e.g., logos) in images is a critical yet challenging problem. It becomes more difficult when target objects differ significantly from the query object...
In this paper, we introduce an information theoretic method for estimating the usefulness of the hyperlink structure induced from the set of retrieved documents. We evaluate the e...