Creating Semantic Representations

摘要: In this chapter, we present the vector space model and some ways to further process such a representation: With feature hashing, random indexing, latent semantic analysis, non-negative matrix factorization, explicit analysis word embedding, or text may be associated with distributed representation. Deep learning, networks auxiliary non-linguistic information provide means for creating representations from linguistic data. We point few of methods datasets used evaluate many different algorithms that create representation, also problems representations.