Entity matching in Master Data Management (MDM) is the task of determining if two entities represent the same real world entity. Entities are typically people, organizations, locations, and events represented as attributed nodes in a graph, though they can also be represented as relational data. While artificial neural network models and probabilistic matching engines exist for this task, explaining entity matching has received less attention. In this presentation, we describe three entity matching scenarios in the real world and present explainability solutions for them.
Balaji Ganesan (IBM Research)
I'm a Research Engineer interested in Information Retrieval and Natural Language Processing. I'm currently working on Enterprise Knowledge Graphs and focusing on Link Prediction using Graph Neural Networks. I'm also concerned with explainability, fairness and ethical considerations in this area of research.
Soma Shekar Naganna (IBM)
More from the Same Authors
2021 : Towards Automated Evaluation of Explanations in Graph Neural Networks »
· Balaji Ganesan · Devbrat Sharma
2021 : Re-imagining GNN Explanations with ideas from Tabular Data »
· Anjali Singh · Shamanth Nayak K · Balaji Ganesan
2021 : Demo of the application »
Soma Shekar Naganna
2021 : Presentation with slides »