The Impact of Different Vector Space Models and Supplementary Techniques on Russian Semantic Similarity Task

Компьютерная лингвистика и интеллектуальные технологии. 2015. Vol. 2. No. 14. P. 145–154.

Лопухин К. А., Lopukhina A., Носырев Г. В.

This paper presents a system for determining semantic similarity between words that was an entry for the Dialog 2015 Russian semantic similarity competition. The system introduced is primary based on word vector models, supplemented with various other methods, both corpus- and dictionary-based. In this paper we compare performance of two methods for building word vectors (word2vec and GloVe), evaluate how performance varies on different corpus sizes and preprocessing techniques, and measure accuracy gains from supplementary methods. We compare system performance on word relatedness and word association tasks, and it turns out that different methods have varying relative importance for these tasks.

Keywords: machine learning, associations, semantic similarity of words, semantic vectors, vector space model