Wikidata5M-SI



Item Type: Dataset
Title: Wikidata5M-SI
Date: 7 October 2023
Creator : Kochsiek, Adrian ORCID: https://orcid.org/0000-0003-1972-1425
Divisions: School of Business Informatics and Mathematics > Praktische Informatik I (Gemulla 2014-)
DDC
Classification:		 004 Computer science, internet
Keywords: semi-inductive; link prediction; knowledge graph; unseen entity
Abstract: Semi-inductive link prediction (LP) in knowledge graphs (KG) is the task of predicting facts for new, previously unseen entities based on context information. Although new entities can be integrated by retraining the model from scratch in principle, such an approach is infeasible for large-scale KGs, where retraining is expensive and new entities may arise frequently. In this paper, we propose and describe a large-scale benchmark to evaluate semi-inductive LP models. The benchmark is based on and extends Wikidata5M: It provides transductive, k-shot, and 0-shot LP tasks, each varying the available information from (i) only KG structure, to (ii) including textual mentions, and (iii) detailed descriptions of the entities. We report on a small study of recent approaches and found that semi-inductive LP performance is far from transductive performance on long-tail entities throughout all experiments. The benchmark provides a test bed for further research into integrating context and textual information in semi-inductive LP models.

Metadata export

FileFilename / InfosLink
[img] Archive
Filename: wikidata5m-si.tar.gz


Download (1GB)
Note: @inproceedings{kochsiek2023benchmark, title={A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphs}, author={Kochsiek, Adrian and Gemulla, Rainer}, booktitle={Findings of the Association for Computational Linguistics: EMNLP 2023}, year={2023} }
Depositing User: Adrian Kochsiek
Date Deposited: 14 Nov 2023 17:22
Last Modified: 01 Mar 2024 07:31

Actions (login required)

View Item View Item
Mannheim Research Data is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.