Information Planning for Text Data

02/09/2018

∙

Information planning enables faster learning with fewer training examples. It is particularly applicable when training examples are costly to obtain. This work examines the advantages of information planning for text data by focusing on three supervised models: Naive Bayes, supervised LDA and deep neural networks. We show that planning based on entropy and mutual information outperforms random selection baseline and therefore accelerates learning.

READ FULL TEXT

Information Planning for Text Data

An information-Theoretic Approach to Semi-supervised Transfer Learning

Learning from networked examples in a k-partite graph

When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?

Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?

Statistically adaptive learning for a general class of cost functions (SA L-BFGS)

Learning More From Less: Towards Strengthening Weak Supervision for Ad-Hoc Retrieval

Demonstrating PAR4SEM - A Semantic Writing Aid with Adaptive Paraphrasing

Information Planning for Text Data

Related Research

An information-Theoretic Approach to Semi-supervised Transfer Learning

Learning from networked examples in a k-partite graph

When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?

Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?

Statistically adaptive learning for a general class of cost functions (SA L-BFGS)

Learning More From Less: Towards Strengthening Weak Supervision for Ad-Hoc Retrieval

Demonstrating PAR4SEM - A Semantic Writing Aid with Adaptive Paraphrasing