Recursive Autoencoder
(Redirected from RAE)
A Recursive Autoencoder is an autoencoder that ...
References
2015
- (Goldberg, 2015) ⇒ Yoav Goldberg. (2015). “A Primer on Neural Network Models for Natural Language Processing.” In: Technical Report Journal, October 5, 2015.
- QUOTE: Other unsupervised approaches, including autoencoders and recursive autoencoders, also fall out of scope.
2011
- (Socher et al., 2011) ⇒ Richard Socher, Jeffrey Pennington, Eric H. Huang, Andrew Y. Ng, and Christopher D. Manning. (2011). “Semi-supervised Recursive Autoencoders for Predicting Sentiment Distributions.” In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. ISBN:978-1-937284-11-4
- QUOTE: We introduce a novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions. ...
... Figure 2: Illustration of an application of a recursive autoencoder to a binary tree. ...
... We introduce an approach based on semisupervised, recursive autoencoders (RAE) which use as input continuous word vectors.
- QUOTE: We introduce a novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions. ...