Quantifying Uncertainties in Natural Language Processing Tasks

Abstract

Reliable uncertainty quantification is a first step towards building explainable, transparent, and accountable artificial intelligent systems. Recent progress in Bayesian deep learning has made such quantification realizable. In this paper, we propose novel methods to study the benefits of characterizing model and data uncertainties for natural language processing (NLP) tasks. With empirical experiments on sentiment analysis, named entity recognition, and language modeling using convolutional and recurrent neural network models, we show that explicitly modeling uncertainties is not only necessary to measure output confidence levels, but also useful at enhancing model performances in various NLP tasks.

arXiv commentTo appear at AAAI 2019

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Recurrent Neural Network Regularization
• Weight Uncertainty in Neural Networks
• Convolutional Neural Networks for Sentence Classification
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

Cited by in corpus (2)

• Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
• Confidence-Guided Learning Process for Continuous Classification of Time Series