Grégoire Montavon


2017

pdf bib
Explaining Recurrent Neural Network Predictions in Sentiment Analysis
Leila Arras | Grégoire Montavon | Klaus-Robert Müller | Wojciech Samek
Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions. In the present work, we extend the usage of LRP to recurrent neural networks. We propose a specific propagation rule applicable to multiplicative connections as they arise in recurrent network architectures such as LSTMs and GRUs. We apply our technique to a word-based bi-directional LSTM model on a five-class sentiment prediction task, and evaluate the resulting LRP relevances both qualitatively and quantitatively, obtaining better results than a gradient-based related method which was used in previous work.

2016

pdf bib
Explaining Predictions of Non-Linear Classifiers in NLP
Leila Arras | Franziska Horn | Grégoire Montavon | Klaus-Robert Müller | Wojciech Samek
Proceedings of the 1st Workshop on Representation Learning for NLP