Muñoz, E;
Minervini, P;
Nickles, M;
(2019)
Embedding cardinality constraints in neural link predictors.
In:
Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing.
(pp. pp. 2243-2250).
The Association for Computing Machinery: New York (NY), USA.
Preview |
Text
Minervini_Embedding cardinality constraints in neural link predictors_AAM.pdf - Accepted Version Download (888kB) | Preview |
Abstract
Neural link predictors learn distributed representations of entities and relations in a knowledge graph. They are remarkably powerful in the link prediction and knowledge base completion tasks, mainly due to the learned representations that capture important statistical dependencies in the data. Recent works in the area have focused on either designing new scoring functions or incorporating extra information into the learning process to improve the representations. Yet the representations are mostly learned from the observed links between entities, ignoring commonsense or schema knowledge associated with the relations in the graph. A fundamental aspect of the topology of relational data is the cardinality information, which bounds the number of predictions given for a relation between a minimum and maximum frequency. In this paper, we propose a new regularisation approach to incorporate relation cardinality constraints to any existing neural link predictor without affecting their efficiency or scalability. Our regularisation term aims to impose boundaries on the number of predictions with high probability, thus, structuring the embeddings space to respect commonsense cardinality assumptions resulting in better representations. Experimental results on Freebase, WordNet and YAGO show that, given suitable prior knowledge, the proposed method positively impacts the predictive accuracy of downstream link prediction tasks.
Type: | Proceedings paper |
---|---|
Title: | Embedding cardinality constraints in neural link predictors |
Event: | SAC '19 Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing |
Location: | Limassol, Cyprus |
Dates: | 8th-12th April 2019 |
ISBN-13: | 978-1-4503-5933-7 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1145/3297280.3297502 |
Publisher version: | https://dx.doi.org/10.1145/3297280.3297502 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Computing methodologies, Artificial intelligence, Knowledge representation and reasoning, Semantic networks, Machine learning, Machine learning approaches, Logical and relational learning, Statistical relational learning |
UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10075181 |
Archive Staff Only
![]() |
View Item |