Research in Computing Science, Vol. 70, pp. 57-68, 2013.
Abstract: Semantic relatedness is a well known problem with its significance ranging from computational linguistics to Natural language Processing applications. Relatedness computation is restricted by the amount of common sense and background knowledge required to relate any two terms. This paper proposes a novel model of relatedness using context profile built on features extracted from encyclopedic knowledge. Proposed research makes use of Wikipedia to represent the context of a word in the high dimensional space of Wikipedia labels. Semantic relatedness of a word pair is then assessed by comparing their corresponding context profiles based on three different weighting schemes using traditional Cosine similarity metrics. To evaluate proposed relatedness approach, three well known benchmark datasets are used and it is shown that Wikipedia article contents can be used effectively to compute term relatedness. The experiments demonstrate that the proposed approach is computationally cheap as well as effective when correlated with human judgments.
PDF: CPRel: Semantic Relatedness Computation Using Wikipedia based Context Profiles
PDF: CPRel: Semantic Relatedness Computation Using Wikipedia based Context Profiles