On aligning OpenIE extractions with Knowledge Bases: A case study

Gashteovski, Kiril ; Gemulla, Rainer ; Kotnis, Bhushan ; Hertling, Sven ; Meilicke, Christian

PDF
On Aligning OpenIE Extractions with Knowledge Bases A Case Study.pdf - Veröffentlichte Version
Download (497kB)

DOI:	https://doi.org/10.18653/v1/2020.eval4nlp-1.14
URL:	https://madoc.bib.uni-mannheim.de/61524
Weitere URL:	https://aclanthology.org/2020.eval4nlp-1.14
URN:	urn:nbn:de:bsz:180-madoc-615240
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2020
Buchtitel:	Evaluation and Comparison of NLP Systems : proceedings of the first workshop, november 20, 2020
Seitenbereich:	143-154
Veranstaltungstitel:	EMNLP 2020
Veranstaltungsort:	Online
Veranstaltungsdatum:	16.-20.11.2020
Herausgeber:	Eger, Steffen ; Gao, Yang ; Peyrard, Maxime ; Zhao, Wei ; Hovy, Eduard
Ort der Veröffentlichung:	Stroudsburg, PA 18360, USA
Verlag:	Association for Computational Linguistics (ACL)
ISBN:	978-1-952148-82-8
Verwandte URLs:	https://www.researchgate.net/publication... https://aclanthology.org/2020.eval4nlp-1...
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Practical Computer Science I: Data Analytics (Gemulla 2014-)
Bereits vorhandene Lizenz:	Creative Commons Namensnennung 4.0 International (CC BY 4.0)
Fachgebiet:	004 Informatik
Abstract:	Open information extraction (OIE) is the task of extracting relations and their corresponding arguments from a natural language text in un- supervised manner. Outputs of such systems are used for downstream tasks such as ques- tion answering and automatic knowledge base (KB) construction. Many of these downstream tasks rely on aligning OIE triples with refer- ence KBs. Such alignments are usually eval- uated w.r.t. a specific downstream task and, to date, no direct manual evaluation of such alignments has been performed. In this paper, we directly evaluate how OIE triples from the OPIEC corpus are related to the DBpedia KB w.r.t. information content. First, we investigate OPIEC triples and DBpedia facts having the same arguments by comparing the information on the OIE surface relation with the KB rela- tion. Second, we evaluate the expressibility of general OPIEC triples in DBpedia. We in- vestigate whether—and, if so, how—a given OIE triple can be mapped to a single KB fact. We found that such mappings are not always possible because the information in the OIE triples tends to be more specific. Our evalua- tion suggests, however, that significant part of OIE triples can be expressed by means of KB formulas instead of individual facts.
Zusätzliche Informationen:	Online-Ressource

	Dieser Eintrag ist Teil der Universitätsbibliographie.
	Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Suche Autoren in

BASE: Gashteovski, Kiril ; Gemulla, Rainer ; Kotnis, Bhushan ; Hertling, Sven ; Meilicke, Christian

Google Scholar: Gashteovski, Kiril ; Gemulla, Rainer ; Kotnis, Bhushan ; Hertling, Sven ; Meilicke, Christian

ORCID: Gashteovski, Kiril, Gemulla, Rainer