We report on the first structured distributional semantic model for Croatian, DM.HR. It is constructed after the model of the English Distributional Memory (Baroni and Lenci, 2010), from a dependencyparsed Croatian web corpus, and covers about 2M lemmas. We give details on the linguistic processing and the design principles. An evaluation shows state-of-theart performance on a semantic similari...

This paper investigates the use and the prediction potential of semantic similarity measures for automatic generation of links across different documents and passages. First, the correlation between the way people link content and the results produced by standard semantic similarity measures is investigated. The relation between semantic similarity and the length of the documents is then also a...

The present paper is devoted to the calculation of semantic similarity between facts. A fact is considered as a single sentence including three parts, “what happened”, “where” and “when”. We propose a function calculating the semantic similarity and provide some experimental results