Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Triple Classification Using Regions and Fine-Grained Entity Typing

 
: Dong, Tiansi; Wang, Zhigang; Li, Juanzi; Bauckhage, Christian; Cremers, Armin B.

:
Postprint urn:nbn:de:0011-n-5523656 (1.0 MByte PDF)
MD5 Fingerprint: 9d884512b2cf0c502e2e9a6c524e89c2
Erstellt am: 31.7.2019


Association for the Advancement of Artificial Intelligence -AAAI-:
The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019. The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019. The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 : Honolulu, Hawaii, USA, January 27 - February 1, 2019
Menlo Park: AAAI Press, 2019
ISBN: 978-1-57735-809-1
S.77-85
Conference on Artificial Intelligence (AAAI) <33, 2019, Honolulu/Hawaii>
Innovative Applications of Artificial Intelligence Conference (IAAI) <31, 2019, Honolulu/Hawaii>
Symposium on Educational Advances in Artificial Intelligence (EAAI) <9, 2019, Honolulu/Hawaii>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()

Abstract
A Triple in knowledge-graph takes a form that consists of head, relation, tail. Triple Classification is used to determine the truth value of an unknown Triple. This is a hard task for 1-to-N relations using the vector-based embedding approach. We propose a new region-based embedding approach using fine-grained type chains. A novel geometric process is presented to extend the vectors of pre-trained entities into n-balls (n-dimensional balls) under the condition that head balls shall contain their tail balls. Our algorithm achieves zero energy loss, therefore, serves as a case study of perfectly imposing tree structures into vector space. An unknown Triple (h, r, x) will be predicted as true, when x's n-ball is located in the r-subspace of h's n-ball, following the same construction of know n tails of h. The experiments are based on large datasets derived from the benchmark datasets WN11, FB13, and WN18. Our results show that the performance of the new method is related to the length of the type chain and the quality of pre-trained entity-embeddings, and that performances of long chains with well-trained entity-embeddings outperform other methods in the literature.

: http://publica.fraunhofer.de/dokumente/N-552365.html