On completing sparse knowledge base with transitive relation embedding

Zili ZHOU, Shaowu LIU, Guandong XU, Wu ZHANG

Research output: Chapter in Book/Report/Conference proceedingChapters

8 Citations (Scopus)

Abstract

Multi-relation embedding is a popular approach to knowledge base completion that learns embedding representations of entities and relations to compute the plausibility of missing triplet. The effectiveness of embedding approach depends on the sparsity of KB and falls for infrequent entities that only appeared a few times. This paper addresses this issue by proposing a new model exploiting the entity-independent transitive relation patterns, namely Transitive Relation Embedding (TRE). The TRE model alleviates the sparsity problem for predicting on infrequent entities while enjoys the generalisation power of embedding. Experiments on three public datasets against seven baselines showed the merits of TRE in terms of knowledge base completion accuracy as well as computational complexity. Copyright © 2019 Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Original languageEnglish
Title of host publicationProceedings of 33rd AAAI Conference on Artificial Intelligence, AAAI 2019
Place of PublicationUSA
PublisherAAAI press
Pages3125-3132
ISBN (Electronic)9781577358091
DOIs
Publication statusPublished - 2019

Citation

Zhou, Z., Liu, S., Xu, G., & Zhang, W. (2019). On completing sparse knowledge base with transitive relation embedding. In Proceedings of 33rd AAAI Conference on Artificial Intelligence, AAAI 2019 (pp. 3125-3132). AAAI press. https://doi.org/10.1609/aaai.v33i01.33013125

Fingerprint

Dive into the research topics of 'On completing sparse knowledge base with transitive relation embedding'. Together they form a unique fingerprint.