%0 Conference Paper %1 ristoski2017largescale %A Ristoski, Petar %A Faralli, Stefano %A Ponzetto, Simone Paolo %A Paulheim, Heiko %B Proceedings of the International Conference on Web Intelligence %C New York, NY, USA %D 2017 %E Sheth, Amit P. %E Ngonga, Axel %E Wang, Yin %E Chang, Elizabeth %E Slezak, Dominik %E Franczyk, Bogdan %E Alt, Rainer %E Tao, Xiaohui %E Unland, Rainer %I ACM %K embeddings induction learning ontology taxonomy word %P 81--87 %R 10.1145/3106426.3106465 %T Large-scale taxonomy induction using entity and word embeddings. %U http://doi.acm.org/10.1145/3106426.3106465 %X Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies. However, building taxonomies manually is a costly endeavor, and hence, automatic methods for taxonomy induction are a good alternative to build large-scale taxonomies. In this paper, we propose TIEmb, an approach for automatic unsupervised class subsumption axiom extraction from knowledge bases using entity and text embeddings. We apply the approach on the WebIsA database, a database of subsumption relations extracted from the large portion of the World Wide Web, to extract class hierarchies in the Person and Place domain. %@ 978-1-4503-4951-2

@inproceedings{ristoski2017largescale, abstract = {Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies. However, building taxonomies manually is a costly endeavor, and hence, automatic methods for taxonomy induction are a good alternative to build large-scale taxonomies. In this paper, we propose TIEmb, an approach for automatic unsupervised class subsumption axiom extraction from knowledge bases using entity and text embeddings. We apply the approach on the WebIsA database, a database of subsumption relations extracted from the large portion of the World Wide Web, to extract class hierarchies in the Person and Place domain.}, acmid = {3106465}, added-at = {2018-01-15T13:18:11.000+0100}, address = {New York, NY, USA}, author = {Ristoski, Petar and Faralli, Stefano and Ponzetto, Simone Paolo and Paulheim, Heiko}, biburl = {https://www.bibsonomy.org/bibtex/21601ddedf17414a76cc2e1560f60e97c/thoni}, booktitle = {Proceedings of the International Conference on Web Intelligence}, description = {Large-scale taxonomy induction using entity and word embeddings}, doi = {10.1145/3106426.3106465}, editor = {Sheth, Amit P. and Ngonga, Axel and Wang, Yin and Chang, Elizabeth and Slezak, Dominik and Franczyk, Bogdan and Alt, Rainer and Tao, Xiaohui and Unland, Rainer}, interhash = {3be4143474019145556b02e7884b2c31}, intrahash = {1601ddedf17414a76cc2e1560f60e97c}, isbn = {978-1-4503-4951-2}, keywords = {embeddings induction learning ontology taxonomy word}, location = {Leipzig, Germany}, numpages = {7}, pages = {81--87}, publisher = {ACM}, series = {WI '17}, timestamp = {2018-01-15T13:18:11.000+0100}, title = {Large-scale taxonomy induction using entity and word embeddings.}, url = {http://doi.acm.org/10.1145/3106426.3106465}, year = 2017 }