To support more effective searches in large-scale weaklytagged image collections, we have developed a novel algorithm to integrate both the visual similarity contexts between the...
This paper presents a new method for Word Sense Disambiguation based on the WordNet Domains lexical resource [4]. The underlaying working hypothesis is tha...
To date, parsers have made limited use of semantic information, but there is evidence to suggest that semantic features can enhance parse disambiguation. This paper shows that sem...
Abstract— In this paper we suggest a new approach to represent text document collections, integrating background knowledge to improve clustering effectiveness. Background knowled...