Combining word representations for measuring word relatedness and similarity
Many unsupervised methods, such as Latent Semantic Analysis and Latent Dirichlet Allocation, have been proposed to automatically infer word representations in the form of a vector. By representing a word by a vector, one can exploit the power of vector algebra to solve many Natural Language Processing tasks e.g. by computing the cosine similarity between the corresponding word vectors the semantic similarity between the two words can be captured. In this paper, we hypothesize that combining different word representations complements the coverage of semantic aspects of a word and thus better represents the word than the individual representations. To this end, we present two approaches of combining word representations obtained from many heterogeneous sources. We also report empirical results for word-to-word semantic similarity and relatedness by using the new representation using two existing benchmark datasets.
Proceedings of the 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015
Niraula, N., Gautam, D., Banjade, R., Maharjan, N., & Rus, V. (2015). Combining word representations for measuring word relatedness and similarity. Proceedings of the 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015, 199-204. Retrieved from https://digitalcommons.memphis.edu/facpubs/2620