The Explanation Game: Towards Prediction Explainability through Sparse Comm

Priberam Labs

Abstract:Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier’s decision. We use this framework to compare several prior approaches for extracting explanations, including gradient methods, representation erasure, and attention mechanisms, in terms of their communication success. In addition, we reinterpret these methods at the light of classical feature selection, and we use this as inspiration to propose new embedded methods for explainability, through the use of selective, sparse attention. Experiments in text classification and natural language inference, using different configurations of explainers and laypeople (including both machines and humans), reveal an advantage of attention-based explainers over gradient and erasure methods. Human experiments show promising results on text classification with post-hoc explainers trained to optimize communication success.Bio:Marcos is a Ph.D. student in the DeepSPIN Project, supervised by André Martins. His main interests include semi-parametric models and explainability of neural networks. Previously, he obtained an M.Sc. degree in Computer Science and Computational Mathematics at the University of São Paulo (USP), having worked with NLP and Machine Learning for sentence segmentation and disfluency detection. Marcos was also a research AI Intern at Unbabel in 2018, where he contributed to the OpenKiwi project.<a href="https://www.priberam.com/" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">www.priberam.com</a>

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

The Explanation Game: Towards Prediction Explainability through Sparse Comm

More events from Priberam Labs

Discover more events from Priberam Labs, from Science & Tech to other experiences you might love.

Still looking for the right event?

Explore all online events to browse and filter by date, category, and more.

The Explanation Game: Towards Prediction Explainability through Sparse Comm

More events from Priberam Labs

Discover more events from Priberam Labs, from Science & Tech to other experiences you might love.

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.

Still looking for the right event?

Explore all online events to browse and filter by date, category, and more.