3 papers
cs.CL2022
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods
Josip Jukić, Martin Tutek, Jan Šnajder
A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component. A common practice…
cs.CL2020
Staying True to Your Word: (How) Can Attention Become Explanation?
Martin Tutek, Jan Šnajder
The attention mechanism has quickly become ubiquitous in NLP. In addition to improving performance of models, attention has been widely used as a glimpse into the inner workings of…
cs.CL2018
Iterative Recursive Attention Model for Interpretable Sequence Classification
Martin Tutek, Jan Šnajder
Natural language processing has greatly benefited from the introduction of the attention mechanism. However, standard attention models are of limited interpretability for tasks tha…