Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
Authors:
Open Access
- 31 May 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1995-2010
Abstract
In the active research area of employing embedding models for knowledge graph completion, particularly for the task of link prediction, most prior studies used two benchmark datasets FB15k and WN18 in evaluating such models. Most triples in these and other datasets in such studies belong to reverse and duplicate relations which exhibit high data redundancy due to semantic duplication, correlation or data incompleteness. This is a case of excessive data leakage---a model is trained using features that otherwise would not be available when the model needs to be applied for real prediction. There are also Cartesian product relations for which every triple formed by the Cartesian product of applicable subjects and objects is a true fact. Link prediction on the aforementioned relations is easy and can be achieved with even better accuracy using straightforward rules instead of sophisticated embedding models. A more fundamental defect of these models is that the link prediction scenario, given such data, is non-existent in the real-world. This paper is the first systematic study with the main objective of assessing the true effectiveness of embedding models when the unrealistic triples are removed. Our experiment results show these models are much less accurate than what we used to perceive. Their poor accuracy renders link prediction a task without truly effective automated solution. Hence, we call for re-investigation of possible effective approaches.Keywords
All Related Versions
Funding Information
- National Science Foundation (IIS-1719054, IIS-1937143)
This publication has 26 references indexed in Scilit:
- Fast rule mining in ontological knowledge bases with AMIE $+$ +The VLDB Journal, 2015
- Observed versus latent features for knowledge base and text inference2015
- Modeling Relation Paths for Representation Learning of Knowledge Bases2015
- Knowledge Graph Embedding via Dynamic Mapping Matrix2015
- WikidataCommunications of the ACM, 2014
- Information Extraction over Structured Data: Question Answering with Freebase2014
- YAGO: A Large Ontology from Wikipedia and WordNetJournal of Web Semantics, 2008
- Freebase2008
- DBpedia: A Nucleus for a Web of Open Data2007
- WordNetCommunications of the ACM, 1995