On evaluating embedding models for knowledge base completion

Wang, Yanjie ; Ruffiinelli, Daniel ; Gemulla, Rainer ; Broscheit, Samuel ; Meilicke, Christian

On Evaluating Embedding Models for Knowledge Base Completion.pdf - Published

Download (498kB)

URL: https://madoc.bib.uni-mannheim.de/52546
Additional URL: https://arxiv.org/abs/1810.07180
URN: urn:nbn:de:bsz:180-madoc-525462
Document Type: Conference or workshop publication
Year of publication: 2019
Book title: The 4th Workshop on Representation Learning for NLP (RepL4NLP-2019) - proceedings of the workshop : August 2, 2019, Florence, Italy : ACL 2019
Page range: 104-112
Conference title: RepL4NLP-2019
Location of the conference venue: Florence, Italy
Date of the conference: 28.7.-2.8.2019
Publisher: Augenstein, Isabelle
Place of publication: Florence, Italy
Publishing house: Association for Computational Linguistics
Related URLs:
Publication language: English
Institution: School of Business Informatics and Mathematics > Practical Computer Science I: Data Analytics (Gemulla 2014-)
License: CC BY 4.0 Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject: 004 Computer science, internet
Abstract: Knowledge graph embedding models have recently received significant attention in the literature. These models learn latent semantic representations for the entities and relations in a given knowledge base; the representations can be used to infer missing knowledge. In this paper, we study the question of how well recent embedding models perform for the task of knowledge base completion, i.e., the task of inferring new facts from an incomplete knowledge base. We argue that the entity ranking protocol, which is currently used to evaluate knowledge graph embedding models, is not suitable to answer this question since only a subset of the model predictions are evaluated. We propose an alternative entity-pair ranking protocol that considers all model predictions as a whole and is thus more suitable to the task. We conducted an experimental study on standard datasets and found that the performance of popular embeddings models was unsatisfactory under the new protocol, even on datasets that are generally considered to be too easy. Moreover, we found that a simple rule-based model often provided superior performance. Our findings suggest that there is a need for more research into embedding models as well as their training strategies for the task of knowledge base completion.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item