activity
20152022
most citedPost-hoc explanation of black-box classifiers using confident itemsets

122 citations · 218 across the 11 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.AI202027 cited

Explaining Black-box Models for Biomedical Text Classification

Milad Moradi, Matthias Samwald

In this paper, we propose a novel method named Biomedical Confident Itemsets Explanation (BioCIE), aiming at post-hoc explanation of black-box machine learning models for biomedica…

cs.LG2020

Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs

Simon Ott, Laura Graf, Asan Agibetov +2

Neural embedding-based machine learning models have shown promise for predicting novel links in biomedical knowledge graphs. Unfortunately, their practical utility is diminished by…

cs.AI2020

Explaining black-box text classifiers for disease-treatment information extraction

Milad Moradi, Matthias Samwald

Deep neural networks and other intricate Artificial Intelligence (AI) models have reached high levels of accuracy on many biomedical natural language processing tasks. However, the…

cs.AI20207 cited

Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes

Asan Agibetov, Matthias Samwald

Recently, link prediction algorithms based on neural embeddings have gained tremendous popularity in the Semantic Web community, and are extensively used for knowledge graph comple…

cs.AI2020122 cited

Post-hoc explanation of black-box classifiers using confident itemsets

Milad Moradi, Matthias Samwald

Black-box Artificial Intelligence (AI) methods, e.g. deep neural networks, have been widely utilized to build predictive models that can extract complex relationships in a dataset…

cs.AI2020

Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules

Ernesto Jiménez-Ruiz, Asan Agibetov, Jiaoyan Chen +2

Large ontologies still pose serious challenges to state-of-the-art ontology alignment systems. In this paper we present an approach that combines a neural embedding model and logic…