Explaining Recurrent Neural Network Predictions in Sentiment Analysis

By Leila Arras, Grgoire Montavon, K. Müller, Wojciech Samek. 2017

385 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Sentiment & Opinion Analysis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Wojciech Samek
  2. K. Müller
  3. Yonatan Belinkov
  4. Yoshua Bengio
  5. Grgoire Montavon
  6. Mohit Bansal
  7. Percy Liang
  8. Yoav Goldberg

In Sentiment & Opinion Analysis

  1. Wojciech Samek
  2. K. Müller
  3. Yonatan Belinkov
  4. Francesca Toni
  5. Piyawat Lertvittayakumjorn
  6. Grgoire Montavon
  7. Sebastian Lapuschkin
  8. Cuntai Guan

Citations in the corpus