Search Results for author:
Found 26 papers, 15 papers with code
Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding
Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa.
Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges
Specifically, we apply three state-of-the-art prototype-based models, ProtoPNet, BRAIxProtoPNet++ and PIP-Net on mammography images for breast cancer prediction and evaluate these models w. r. t.
PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans
Information from neuroimaging examinations (CT, MRI) is increasingly used to support diagnoses of dementia, e. g., Alzheimer's disease.
A Second Look on BASS -- Boosting Abstractive Summarization with Unified Semantic Graphs -- A Replication Study
We present a detailed replication study of the BASS framework, an abstractive summarization system based on the notion of Unified Semantic Graphs.
The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs
In this work, we consider a complementary aspect, namely the coherency of factual knowledge in PLMs, i. e., how often can PLMs predict the subject entity given its initial prediction of the object entity.
InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification
Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness.
Explainable Bayesian Optimization
In industry, Bayesian optimization (BO) is widely applied in the human-AI collaborative parameter tuning of cyber-physical systems.
Feature Attribution Explanations for Spiking Neural Networks
We present \textit{Temporal Spike Attribution} (TSA), a local explanation method for SNNs.
Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models
Our contributions are: (1) We propose a categorization scheme for factual probing methods that is based on how their inputs, outputs and the probed PLMs are adapted; (2) We provide an overview of the datasets used for factual probing; (3) We synthesize insights about knowledge retention and prompt optimization in PLMs, analyze obstacles to adopting PLMs as knowledge bases and outline directions for future work.
Weakly Supervised Learning for Breast Cancer Prediction on Mammograms in Realistic Settings
We show that two-level MIL can be applied in realistic clinical settings where only case labels, and a variable number of images per patient are available.
Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i. e., their prediction is based on undesired auxiliary features which are strongly correlated with class labels but lack causal reasoning.
The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers
Interpretable part-prototype models are computer vision models that are explainable by design.
Guidance in Radiology Report Summarization: An Empirical Evaluation and Error Analysis
Automatically summarizing radiology reports into a concise impression can reduce the manual burden of clinicians and improve the consistency of reporting.
Interpreting and Correcting Medical Image Classification with PIP-Net
We conclude that part-prototype models are promising for medical applications due to their interpretability and potential for advanced model debugging.
PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification
Driven by the principle of explainability-by-design, we introduce PIP-Net (Patch-based Intuitive Prototypes Network): an interpretable image classification model that learns prototypical parts in a self-supervised fashion which correlate better with human vision.
Patient-friendly Clinical Notes: Towards a new Text Simplification Dataset
Automatic text simplification can help patients to better understand their own clinical notes.
Explaining Machine Learning Models in Natural Conversations: Towards a Conversational XAI Agent
In this work, we show how to incorporate XAI in a conversational agent, using a standard design for the agent comprising natural language understanding and generation components.
Explainable Artificial Intelligence (XAI)
Natural Language Understanding
Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers
We complement previous surveys by providing a comprehensive analysis of recently published methods that deploy deep learning approaches.
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practices of more than 300 papers published in the last 7 years at major AI and ML conferences that introduce an XAI method.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Towards a trustworthy, secure and reliable enclave for machine learning in a hospital setting: The Essen Medical Computing Platform (EMCP)
AI/Computing at scale is a difficult problem, especially in a health care setting.
Neural Prototype Trees for Interpretable Fine-grained Image Recognition
We propose the Neural Prototype Tree (ProtoTree), an intrinsically interpretable deep learning method for fine-grained image recognition.
This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition
By explaining such 'misleading' prototypes, we improve the interpretability and simulatability of a prototype-based classification model.
Automated Retrieval of ATT&CK Tactics and Techniques for Cyber Threat Reports
Over the last years, threat intelligence sharing has steadily grown, leading cybersecurity professionals to access increasingly larger amounts of heterogeneous data.
Comparing Rule-based, Feature-based and Deep Neural Methods for De-identification of Dutch Medical Records
We test the generalizability of three de-identification methods across languages and domains.
How model accuracy and explanation fidelity influence user trust
We also found that users cannot be tricked by high-fidelity explanations into having trust for a bad classifier.
Causal Discovery with Attention-Based Convolutional Neural Networks
We therefore present the Temporal Causal Discovery Framework (TCDF), a deep learning framework that learns a causal graph structure by discovering causal relationships in observational time series data.
