KATE: K-Competitive Autoencoder for Text
This addresses the challenge of learning effective text representations for NLP tasks, though it appears incremental as it builds on existing autoencoder frameworks.
The paper tackled the problem of autoencoders learning trivial representations for text due to high-dimensionality and sparsity, and proposed KATE, a k-competitive autoencoder that learns meaningful representations, outperforming traditional autoencoders and other models in tasks like document classification and retrieval.
Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations of text documents due to their confounding properties such as high-dimensionality, sparsity and power-law word distributions. In this paper, we propose a novel k-competitive autoencoder, called KATE, for text documents. Due to the competition between the neurons in the hidden layer, each neuron becomes specialized in recognizing specific data patterns, and overall the model can learn meaningful representations of textual data. A comprehensive set of experiments show that KATE can learn better representations than traditional autoencoders including denoising, contractive, variational, and k-sparse autoencoders. Our model also outperforms deep generative models, probabilistic topic models, and even word representation models (e.g., Word2Vec) in terms of several downstream tasks such as document classification, regression, and retrieval.