PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures such as convolutional neural networks, these methods usually yield inferior results when applied to particular machine learning tasks... (read more)

Results in Papers With Code
(↓ scroll down to see all results)