One of the ultimate aims of Natural Language Processing is toautomate the analysis of the meaning of text. A fundamental step in thatdirection consists in enabling effective ways to automatically link textualreferences to their referents, that is, real world objects. The work presentedin this paper addresses the problem of attributing a sense to proper namesin a given text, i.e., automatically associating words representing NamedEntities with their referents. The method for Named Entity Disambiguationproposed here is based on the concept of semantic relatedness, which in thiswork is obtained via a graph-based model over Wikipedia. We show that,without building the traditional bag of words representation of the text,but instead only considering named entities within the text, the proposedmethod achieves results competitive with the state-of-the-art on two differentdatasets.
展开▼
