Machine Learning-Based Semantic Entity Alignment for Multi-Source Data: a Systematic Literature Review

Alex Boyko, Siamak Farshidi, Zhiming Zhao
2021 Zenodo  
It has become more common to store data about real-world entities, where this data is often distributed across multiple data sources. Entity alignment helps with merging and managing such data by identifying and linking similar entities stored in each of the data sources. Many machine learning-based semantic entity alignment approaches have been proposed by the recent studies in the field. The goal of this systematic literature review is to give an overview of the most recent studies that
more » ... s entity alignment, as well as to answer some of the research questions that are formulated based on the current research trends in this field. In this study we investigate and summarize two novel methods to compute semantic similarity, two metrics used to measure the quality of semantic similarity between knowledge base entities, and seven state-of-the-art ML-based semantic entity alignment approaches. We also investigate recent studies that touch upon user experience, privacy preservation, decentralized environment and other properties related to entity alignment. We conclude this study with an overview of the main findings presented in a table and graphic forms. We also present a taxonomy of results that can be used by other researchers in this field to get a clear overview of the most recent ML-based semantic entity alignment methods.
doi:10.5281/zenodo.6328248 fatcat:kl4julgduffzzhyxztsfxzsw3a