LGCLIRNEAug 5, 2015

Learning from LDA using Deep Neural Networks

arXiv:1508.01011v17 citations
Originality Incremental advance
AI Analysis

This addresses the computational bottleneck of LDA for users in natural language processing, but it is incremental as it builds on existing transfer learning methods.

The paper tackles the problem of slow inference in Latent Dirichlet Allocation (LDA) by using a deep neural network (DNN) supervised by LDA to approximate its behavior, resulting in inference speedups of tens to hundreds of times on a document classification task.

Latent Dirichlet Allocation (LDA) is a three-level hierarchical Bayesian model for topic inference. In spite of its great success, inferring the latent topic distribution with LDA is time-consuming. Motivated by the transfer learning approach proposed by~\newcite{hinton2015distilling}, we present a novel method that uses LDA to supervise the training of a deep neural network (DNN), so that the DNN can approximate the costly LDA inference with less computation. Our experiments on a document classification task show that a simple DNN can learn the LDA behavior pretty well, while the inference is speeded up tens or hundreds of times.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes