Header

UZH-Logo

Maintenance Infos

Aligning Knowledge Base and Document Embedding Models using Regularized Multi-Task Learning


Baumgartner, Matthias; Zhang, Wen; Paudel, Bibek; Dell'Aglio, Daniele; Chen, Huajun; Bernstein, Abraham (2018). Aligning Knowledge Base and Document Embedding Models using Regularized Multi-Task Learning. In: The Semantic Web – ISWC 2018, Monterey, CA, USA, 8 October 2018 - 12 October 2018. Springer, 21-37.

Abstract

Knowledge Bases (KBs) and textual documents contain rich and complementary information about real-world objects, as well as relations among them. While text documents describe entities in freeform, KBs organizes such information in a structured way. This makes these two information representation forms hard to compare and integrate, limiting the possibility to use them jointly to improve predictive and analytical tasks. In this article, we study this problem, and we propose KADE, a solution based on a regularized multi-task learning of KB and document embeddings. KADE can potentially incorporate any KB and document embedding learning method. Our experiments on multiple datasets and methods show that KADE effectively aligns document and entities embeddings, while maintaining the characteristics of the embedding models.

Abstract

Knowledge Bases (KBs) and textual documents contain rich and complementary information about real-world objects, as well as relations among them. While text documents describe entities in freeform, KBs organizes such information in a structured way. This makes these two information representation forms hard to compare and integrate, limiting the possibility to use them jointly to improve predictive and analytical tasks. In this article, we study this problem, and we propose KADE, a solution based on a regularized multi-task learning of KB and document embeddings. KADE can potentially incorporate any KB and document embedding learning method. Our experiments on multiple datasets and methods show that KADE effectively aligns document and entities embeddings, while maintaining the characteristics of the embedding models.

Statistics

Citations

Dimensions.ai Metrics
3 citations in Web of Science®
7 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

204 downloads since deposited on 04 Oct 2018
31 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Theoretical Computer Science
Physical Sciences > General Computer Science
Language:English
Event End Date:12 October 2018
Deposited On:04 Oct 2018 08:33
Last Modified:04 Jun 2022 07:05
Publisher:Springer
Number:11136
ISBN:978-3-030-00670-9
Additional Information:ISBN: 978-3-030-00671-6 (E)
OA Status:Green
Publisher DOI:https://doi.org/10.1007/978-3-030-00671-6_2
Related URLs:https://easychair.org/cfp/ssws2018
Other Identification Number:merlin-id:16389
  • Content: Accepted Version