A5014746776- Explainable Artificial Intelligence (XAI)
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Topic Modeling
- Adversarial Robustness in Machine Learning
- Human-Automation Interaction and Safety
- Data Visualization and Analytics
- Scientific Computing and Data Management
- Ethics and Social Impacts of AI
- Autonomous Vehicle Technology and Safety
IBM Research - Ireland
2022-2023
Machine learning technologies are increasingly being applied in many different domains the real world. As autonomous machines and black-box algorithms begin making decisions previously entrusted to humans, great academic public interest has been spurred provide explanations that allow users understand decision-making process of machine model. Besides explanations, Interactive Learning (IML) seeks leverage user feedback iterate on an ML solution correct errors align with those users. Despite...
We propose KnowGL, a tool that allows converting text into structured relational data represented as set of ABox assertions compliant with the TBox given Knowledge Graph (KG), such Wikidata. address this problem sequence generation task by leveraging pre-trained sequence-to-sequence language models, e.g. BART. Given sentence, we fine-tune models to detect pairs entity mentions and jointly generate facts consisting full semantic annotations for KG, labels, types, their relationships. To...
We present AutoDOViz, an interactive user interface for automated decision optimization (AutoDO) using reinforcement learning (RL). Decision (DO) has classically being practiced by dedicated DO researchers where experts need to spend long periods of time fine tuning a solution through trial-and-error. AutoML pipeline search sought make it easier data scientist find the best machine leveraging automation and tune solution. More recently, these advances have been applied domain AutoDO, with...
In real-world applications when deploying Machine Learning (ML) models, initial model development includes close analysis of the results and behavior by a data scientist. Once trained, however, models may need to be retrained with new or updated adhere rules regulations. This presents two challenges. First, how communicate is making its decisions before after retraining, second support editing take into account requirements. To address these needs, we built AIMEE (AI Model Explorer Editor),...
February 01 2020 IEEE VIS 2016 and 2017 Arts Program Gallery Benedikt Groß, Groß Web: https://lab.moovel.com Search for other works by this author on: This Site Google Scholar Raphael Reimann, Reimann Philipp Schmitt, Schmitt Esteban Garcia Bravo, Bravo www.carlsongarcia.com Maxwell Carlson, Carlson Aaron Zernack, Zernack Jorge Garcia, Yoon Chung Han, Han www.yoonchunghan.com Shankar Tiwari, Tiwari Till Nagel, Nagel https://uclab.fh-potsdam.de/cf Christopher Pietsch, Pietsch Mark J. Stock,...
We propose KnowGL, a tool that allows converting text into structured relational data represented as set of ABox assertions compliant with the TBox given Knowledge Graph (KG), such Wikidata. address this problem sequence generation task by leveraging pre-trained sequence-to-sequence language models, e.g. BART. Given sentence, we fine-tune models to detect pairs entity mentions and jointly generate facts consisting full semantic annotations for KG, labels, types, their relationships. To...