Open Universiteit

Please use this identifier to cite or link to this item:
Title: Combining Taxonomies using Word2vec
Authors: Swoboda, Tobias
Hemmje, Matthias
Dascalu, Mihai
Trausan-Matu, Stefan
Keywords: word2vec
taxonomy integration
ontology alignment
automated semantic integration
Issue Date: 2016
Publisher: Association for Computing Machinery
Citation: Swoboda, T., Hemmje, M., Dascalu, M., & Trausan-Matu, S. (2016). Combining Taxonomies using Word2vec. In DocEng 2016 (pp. 131–134). Vienna, Austria: ACM.
Series/Report no.: Proceedings of the 2016 ACM Symposium on Document Engineering;
Abstract: Taxonomies have gained a broad usage in a variety of fields due to their extensibility, as well as their use for classification and knowledge organization. Of particular interest is the digital document management domain in which their hierarchical structure can be effectively employed in order to organize documents into content-specific categories. Common or standard taxonomies (e.g., the ACM Computing Classification System) contain concepts that are too general for conceptualizing specific knowledge domains. In this paper we introduce a novel automated approach that combines sub-trees from general taxonomies with specialized seed taxonomies by using specific Natural Language Processing techniques. We provide an extensible and generalizable model for combining taxonomies in the practical context of two very large European research projects. Because the manual combination of taxonomies by domain experts is a highly time consuming task, our model measures the semantic relatedness between concept labels in CBOW or skip-gram Word2vec vector spaces. A preliminary quantitative evaluation of the resulting taxonomies is performed after applying a greedy algorithm with incremental thresholds used for matching and combining topic labels.
ISBN: 978-1-4503-4438-8
Appears in Collections:1. RAGE Publications

Files in This Item:
File Description SizeFormat 
p131-swoboda.pdf1.15 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons