Use of neighbor sentence co-occurrence to improve word semantic similarity detection

In this paper we present the first result of detecting word semantic similarity on several Russian semantic word similarity datasets inclduing the Russian translations of Miller-Charles and Rubenstein-Goodenough sets, the similarity and relatedness subsets of the Russian translation of WordSim353 set prepared for the first Russian word semantic evaluation Russe-2015. The experiments were carried out on three text collections: Russian Wikipedia, a news collection, and their united collection. We found that the best results in detection of lexical paradigmatic relations were achieved using the combination of word2vec with the new type of features based on word cooccurrences in neighbor sentences.