Staying True to Your Word: (How) Can Attention Become Explanation?

Staying True to Your Word: (How) Can Attention Become Explanation?

19 May 2020

Martin Tutek

Papers citing "Staying True to Your Word: (How) Can Attention Become Explanation?"

8 / 8 papers shown

Title
A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inference Duc Hau Nguyen Duc Hau Nguyen Pascale Sébillot 54 5 0 23 Jan 2025
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods Josip Jukić Martin Tutek Jan Snajder FAtt 24 0 0 15 Nov 2022
Understanding Interlocking Dynamics of Cooperative Rationalization Mo Yu Yang Zhang Shiyu Chang Tommi Jaakkola 20 41 0 26 Oct 2021
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience G. Chrysostomou Nikolaos Aletras 32 16 0 31 Aug 2021
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification G. Chrysostomou Nikolaos Aletras 24 37 0 06 May 2021
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? Jasmijn Bastings Katja Filippova XAI LRM 49 173 0 12 Oct 2020
The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives Elena Voita Rico Sennrich Ivan Titov 207 181 0 03 Sep 2019
Towards A Rigorous Science of Interpretable Machine Learning Finale Doshi-Velez Been Kim XAI FaML 257 3,690 0 28 Feb 2017