An Embedding-Based Topic Model for Document Classification

Topic modeling is an unsupervised learning task that discovers the hidden topics in a collection of documents. In turn, discovered can be used for summarizing, organizing, and understanding documents collection. Most existing techniques topic are derivatives Latent Dirichlet Allocation which uses bag-of-word assumption However, bag-of-words models completely dismiss relationships between words. For this reason, article presents two-stage algorithm modelling leverages word embeddings co-occurrence. first stage, we determine topic-word distributions by soft-clustering random set embedded n -grams from second document-topic sampling each document distributions. This approach distributional properties instead using assumption. Experimental results on various data sets Australian compensation organization show remarkable comparative effectiveness proposed classification.