Leila Arras
Research Associate
Department of Artificial Intelligence
Research group of Explainable Artificial Intelligence
Fraunhofer
Heinrich Hertz Institute HHI
Berlin, Germany
leila.arras@hhi.fraunhofer.de
google scholar
Publications
- Ground Truth Evaluation of Neural Network
Explanations with CLEVR-XAI
-
Leila Arras*, Ahmed Osman*, and Wojciech Samek (*equal contribution)
- arXiv, February
2021. [arXiv:2003.07258v2]
- paper
bibtex dataset
- Causes of Outcome Learning: A causal
inference-inspired machine learning approach to disentangling common
combinations of potential causes of a health outcome
-
Andreas Rieckmann, Piotr Dworzynski, Leila Arras, Sebastian Lapuschkin,
Wojciech Samek, Onyebuchi A. Arah, Naja H. Rod, Claus T. Ekstrom
- medRxiv,
December 2020. [medRxiv:2020.12.10.20225243]
- paper
bibtex
- Explaining the Decisions of Convolutional and
Recurrent Neural Networks
-
Wojciech Samek, Leila Arras, Ahmed Osman, Grégoire Montavon, and
Klaus-Robert Müller
- Chapter in:
Mathematical Aspects of Deep Learning, 2021 (to appear). Cambridge
University Press. [preprint]
- paper
bibtex
- Towards Ground Truth Evaluation of Visual
Explanations
-
Ahmed Osman*, Leila Arras*, and Wojciech Samek (*equal contribution)
- arXiv, March
2020. [arXiv:2003.07258v1]
- paper
bibtex dataset
- Explaining and Interpreting LSTMs
-
Leila Arras*, José Arjona-Medina*, Michael Widrich, Grégoire Montavon,
Michael Gillhofer, Klaus-Robert Müller, Sepp Hochreiter, and Wojciech
Samek (*equal contribution)
- Chapter in:
Explainable AI: Interpreting, Explaining and Visualizing Deep
Learning, LNCS vol 11700, pages
211-238, September 2019. Springer, Cham. doi.org/10.1007/978-3-030-28954-6_11 [arXiv:1909.12114]
- paper bibtex
- Evaluating Recurrent Neural Network Explanations
-
Leila Arras, Ahmed Osman, Klaus-Robert Müller, and Wojciech Samek
- ACL 2019
BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for
NLP (oral presentation), pages 113-126, Florence, Italy, August 2019.
Association for Computational Linguistics. doi.org/10.18653/v1/W19-4813
[arXiv:1904.11829]
- paper bibtex
slides
talk
- Explaining Recurrent Neural Network Predictions in
Sentiment Analysis
-
Leila Arras, Grégoire Montavon, Klaus-Robert Müller, and Wojciech Samek
- EMNLP 2017
Workshop on Computational Approaches to Subjectivity, Sentiment and
Social Media Analysis (WASSA), pages 159-168, Copenhagen, Denmark,
September 2017. Association for Computational Linguistics. doi.org/10.18653/v1/W17-5221
[arXiv:1706.07206]
- paper bibtex
poster
code
- "What is relevant in a text document?": An
interpretable machine learning approach
-
Leila Arras, Franziska Horn, Grégoire Montavon, Klaus-Robert Müller, and
Wojciech Samek
- PLOS ONE
Journal, 12(8):e0181142, August 2017. Public Library of Science. doi.org/10.1371/journal.pone.0181142
- paper bibtex
demo
- Explaining Predictions of Non-Linear Classifiers in
NLP
-
Leila Arras, Franziska Horn, Grégoire Montavon, Klaus-Robert Müller, and
Wojciech Samek
- ACL 2016
Workshop on Representation Learning for NLP (Rep4NLP), pages 1-7,
Berlin, Germany, August 2016. Association for Computational
Linguistics. doi.org/10.18653/v1/W16-1601 [arXiv:1606.07298]
- paper
bibtex
poster
Previous work
- Theoretical and empirical evaluation of data
reduction for exact Kemeny Rank Aggregation
-
Nadja Betzler, Robert Bredereck, and Rolf Niedermeier (Leila Arras in
the Acknowledgments)
- Journal of
Autonomous Agents and Multi-Agent Systems (JAAMAS), 28(5):721-748,
September 2014. Springer US. doi.org/10.1007/s10458-013-9236-y
Publishing Notes
Data Protection
Policy