Can we predict new facts with open knowledge graph embeddings? A benchmark for open link prediction

Broscheit, Samuel ; Gashteovski, Kiril ; Wang, Yanjie ; Gemulla, Rainer

[img] PDF
Can We Predict New Facts with Open Knowledge Graph Embeddings A Benchmark for Open Link Prediction.pdf - Published

Download (648kB)

Additional URL:
URN: urn:nbn:de:bsz:180-madoc-557240
Document Type: Conference or workshop publication
Year of publication: 2020
Book title: ACL 2020 : the 58th Annual Meeting of the Association for Computational Linguistics, proceedings of the conference, ACL 2020The 58th Annual Meeting of theAssociation for Computational LinguisticsProceedings of the Conference, July 5 - 10, 2020
Page range: 2296-2308
Conference title: ACL 2020
Location of the conference venue: Online
Date of the conference: 05.-10.07.2020
Publisher: Jurafsky, Dan
Place of publication: Stroudsburg, PA
Publishing house: Association for Computational Linguistics
ISBN: 978-1-952148-25-5
Publication language: English
Institution: School of Business Informatics and Mathematics > Praktische Informatik I (Gemulla 2014-)
License: CC BY 4.0 Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject: 004 Computer science, internet
Abstract: Open Information Extraction systems extract(“subject text”, “relation text”, “object text”)triples from raw text. Some triples are textualversions of facts, i.e., non-canonicalized men-tions of entities and relations. In this paper, weinvestigate whether it is possible to infernewfacts directly from theopen knowledge graphwithout any canonicalization or any supervi-sion from curated knowledge. For this pur-pose, we propose the open link prediction task,i.e., predicting test facts by completing(“sub-ject text”, “relation text”, ?)questions. Anevaluation in such a setup raises the question ifa correct prediction is actually anewfact thatwas induced by reasoning over the open knowl-edge graph or if it can be trivially explained.For example, facts can appear in different para-phrased textual variants, which can lead to testleakage. To this end, we propose an evaluationprotocol and a methodology for creating theopen link prediction benchmark OLPBENCH.We performed experiments with a prototypicalknowledge graph embedding model for openlink prediction. While the task is very chal-lenging, our results suggests that it is possibleto predict genuinely new facts, which can notbe trivially explained.

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