Explaining Recurrent Neural Network Predictions in Sentiment Analysis
Leila Arras, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
Abstract
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.- Anthology ID:
- W17-5221
- Volume:
- Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Alexandra Balahur, Saif M. Mohammad, Erik van der Goot
- Venue:
- WASSA
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 159–168
- Language:
- URL:
- https://aclanthology.org/W17-5221
- DOI:
- 10.18653/v1/W17-5221
- Cite (ACL):
- Leila Arras, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek. 2017. Explaining Recurrent Neural Network Predictions in Sentiment Analysis. In Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 159–168, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Explaining Recurrent Neural Network Predictions in Sentiment Analysis (Arras et al., WASSA 2017)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/W17-5221.pdf
- Code
- ArrasL/LRP_for_LSTM