Латентное Встраивание Тем

AbstractTopic modeling and word embedding are two important techniques for deriving latent semantics from data. General-purpose topic models typically work in coarse granularity by capturing word co-occurrence at the document/sentence …...

AbstractWhen searching for information, a human reader first glances over a document, spots relevant sections, and then focuses on a few sentences for resolving her intention. However, the high variance …...