Few-shot Learning for Topic Modeling

TL;DR

This paper introduces a neural network-based few-shot learning approach for topic modeling, enabling effective topic extraction from very limited documents by integrating EM algorithm differentiability and episodic training.

Contribution

It presents a novel neural network method that learns topic model priors from few documents, improving upon traditional models that require many documents for training.

Findings

Achieves better perplexity than existing methods on real-world datasets

Effectively learns from just a few documents using episodic training

Integrates EM algorithm into neural network training for topic modeling

Abstract

Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a topic model from just a few documents. The neural networks in our model take a small number of documents as inputs, and output topic model priors. The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM algorithm. Since each step in the EM algorithm is differentiable, the proposed method can backpropagate the loss through the EM algorithm to train the neural networks. The expected test likelihood is maximized by a stochastic gradient descent method using a set of multiple text corpora with an episodic training framework. In our experiments, we demonstrate that the proposed method achieves better perplexity than existing methods using three real-world text document sets.