The article describes our system submitted to the SemEval-2014 task on Aspect-Based Sentiment Analysis. The methods based on distributed representations of words for the aspect term extraction and aspect term polarity detection tasks are presented. The methods for the aspect category detection and category polarity detection tasks are presented as well. Well-known skip-gram model for constructing the distributed representations is briefly described. The results of our methods are shown in comparison with the baseline and the best result.