DeepAI AI Chat
Log In Sign Up

Explaining Predictions of Non-Linear Classifiers in NLP

by   Leila Arras, et al.
Berlin Institute of Technology (Technische Universität Berlin)

Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional neural network (CNN) trained on a topic categorization task. Our analysis highlights which words are relevant for a specific prediction of the CNN. We compare our technique to standard sensitivity analysis, both qualitatively and quantitatively, using a "word deleting" perturbation experiment, a PCA analysis, and various visualizations. All experiments validate the suitability of LRP for explaining the CNN predictions, which is also in line with results reported in recent image classification studies.


"What is Relevant in a Text Document?": An Interpretable Machine Learning Approach

Text documents can be described by a number of abstract concepts such as...

Explaining Recurrent Neural Network Predictions in Sentiment Analysis

Recently, a technique called Layer-wise Relevance Propagation (LRP) was ...

Explaining Prediction Uncertainty of Pre-trained Language Models by Detecting Uncertain Words in Inputs

Estimating the predictive uncertainty of pre-trained language models is ...

Analyzing Classifiers: Fisher Vectors and Deep Neural Networks

Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular an...

It's All in the Name: A Character Based Approach To Infer Religion

Demographic inference from text has received a surge of attention in the...

Learning Mutual Fund Categorization using Natural Language Processing

Categorization of mutual funds or Exchange-Traded-funds (ETFs) have long...

Explaining Face Presentation Attack Detection Using Natural Language

A large number of deep neural network based techniques have been develop...