Natural Language Explanations for Machine Learning Classification Decisions

Burton, James; Al Moubayed, Noura; Enshaei, Amir

Abstract

This paper addresses the challenge of providing understandable explanations for machine learning classification decisions. To do this, we introduce a dataset of expert-written textual explanations paired with numerical explanations, forming a data-to-text generation task. We fine-tune BART and T5 language models on this dataset to generate natural language explanations by linearizing the information represented by explainable output graphs. We find that the models can produce fluent and largely accurate textual explanations. We experiment with various configurations and see that an augmented dataset leads to a reduced error rate. Additionally, we probe the numerical explanations more directly by fine-tuning BART and T5 on a question-answer task and achieved an accuracy of 91% with T5.

Citation

Burton, J., Al Moubayed, N., & Enshaei, A. (2023, June). Natural Language Explanations for Machine Learning Classification Decisions. Presented at 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2023 International Joint Conference on Neural Networks (IJCNN)
• Start Date: Jun 18, 2023
• End Date: Jun 23, 2023
• Acceptance Date: Jun 1, 2023
• Online Publication Date: Aug 2, 2023
• Publication Date: Jun 18, 2023
• Deposit Date: Aug 29, 2023
• Publicly Available Date: Aug 30, 2023
• Series ISSN: 2161-4393
• Book Title: 2023 International Joint Conference on Neural Networks (IJCNN)
• ISBN: 9781665488686
• DOI: https://doi.org/10.1109/ijcnn54540.2023.10191637
• Public URL: https://durham-repository.worktribe.com/output/1726329