Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople,�...
Maximilian Dustin Nasert. Latest. Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods.
Papers by Maximilian Dustin Nasert with links to code and results.
We formalize the underexplored task of translating saliency maps into natural language and compare methods that address two key challenges of this approach.
Oct 13, 2022 � Authors:Nils Feldhus, Leonhard Hennig, Maximilian Dustin Nasert, Christopher Ebert, Robert Schwarzenberg, Sebastian M�ller. View a PDF of the�...
In this position paper, we establish desiderata for Mediators, text-based conversational agents which are capable of explaining the behavior of neural models�...
Oct 13, 2022 � Authors:Nils Feldhus, Leonhard Hennig, Maximilian Dustin Nasert, Christopher Ebert, Robert Schwarzenberg, Sebastian M�ller.
Aug 1, 2024 � Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.
... Maximilian Dustin Nasert and Christopher Ebert and Robert Schwarzenberg and Sebastian M\"{o}ller", booktitle = "Proceedings of the First Workshop on Natural�...
Sep 8, 2024 � We conduct a human evaluation of explanation representations across two natural language processing (NLP) tasks: news topic classification and�...