This notebook explains how to implement doc2vec using PyTorch. It's aimed at relative beginners, but basic understanding of word embeddings (vectors) and PyTorch are assumed. The implementation we end ...

Abstract: The ever-increasing number of electronic content stored in digital libraries requires a significant amount of effort in cataloguing and has led to self-deposit solutions where the authors ...

Abstract: Information recommendation methods mainly include collaborative filtering and content-based. The collaborative filtering method is the most widely used recommendation method. It mainly uses ...

HLTA is a novel method for hierarchical topic detection. Specifically, it models document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at ...