Open Information Extraction on German Wikipedia Texts

Klose C, Gui Z, Harth A (2022)


Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2022

Series: International Knowledge Graph Generation From Text (TEXT2KG)

Book Volume: 3184

Pages Range: 8

Conference Proceedings Title: CEUR Workshop Proceedings (CEUR-WS)

Event location: Crete, Hersonissos, Greece GR

URI: http://ceur-ws.org/Vol-3184/

Abstract

Knowledge Graphs are becoming a fundamental building block for semantic search and voice assistants.
This paper deals with the automated Knowledge Graph Construction from unstructured data. Predominantly, the focus is on Open Information Extraction (Open IE), an unsupervised learning approach that attempts to extract triples from plain text independent of their domain. Hence, it is the first step towards automated Knowledge Graph Construction. Previous work mainly applied Open IE to English texts. In this paper, the focus is on German texts. Due to the lack of German Open Information Extraction datasets, a dataset on the basis of Wikipedia is created. Two Open Information Extraction Systems for German are introduced. Finally, the performance of the systems are evaluated.

Authors with CRIS profile

How to cite

APA:

Klose, C., Gui, Z., & Harth, A. (2022). Open Information Extraction on German Wikipedia Texts. In Sanju Tiwari, Nandana Mihindukulasooriya, Francesco Osborne, Dimitris Kontokostas, Jennifer D’Souza, Mayank Kejriwal, Loris Bozzato, Valentina Anita Carriero, Torsten Hahmann, Antoine Zimmermann (Eds.), CEUR Workshop Proceedings (CEUR-WS) (pp. 8). Crete, Hersonissos, Greece, GR.

MLA:

Klose, Christian, Zhou Gui, and Andreas Harth. "Open Information Extraction on German Wikipedia Texts." Proceedings of the Text2KG 2022: International Workshop on Knowledge Graph Generation from Text, Co-located with the ESWC 2022, Crete, Hersonissos, Greece Ed. Sanju Tiwari, Nandana Mihindukulasooriya, Francesco Osborne, Dimitris Kontokostas, Jennifer D’Souza, Mayank Kejriwal, Loris Bozzato, Valentina Anita Carriero, Torsten Hahmann, Antoine Zimmermann, 2022. 8.

BibTeX: Download