Combining Node Embeddings with Domain Knowledge for Identity Resolution

J. Baas

Research output: Contribution to conferencePaperAcademic

Abstract

The application of powerful and popular machine learning methods on real life historical data generates sub-symbolic models of the data. Such models do not perform well when trained with insufficient (or no) ground truth. We argue that the performance of these models could be improved by incorporating domain-specific knowledge, and propose an approach to incorporate symbolic domain-specific knowledge in the sub-symbolic models of the data. We show with experimental results on real historical data that our approach improves performance.
Original languageEnglish
Number of pages8
Publication statusPublished - 2021
EventGraphs and Networks in the Humanities - Online
Duration: 4 Feb 20225 Feb 2022
Conference number: 6
https://tcdh.uni-trier.de/en/event/graphs-and-networks-humanities-2022-technologies-models-analyses-and-visualizations

Conference

ConferenceGraphs and Networks in the Humanities
Abbreviated titleGraphum
Period4/02/225/02/22
Internet address

Fingerprint

Dive into the research topics of 'Combining Node Embeddings with Domain Knowledge for Identity Resolution'. Together they form a unique fingerprint.

Cite this