Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Fine-grained General Entity Typing in German using GermaNet

Publication

Fine-grained General Entity Typing in German using GermaNet

Weber, Sabine; Steedman, Mark (2021): Fine-grained General Entity Typing in German using GermaNet, in: Alexander Panchenko, Fragkiskos D. Malliaros, Varvara Logacheva, u. a. (Hrsg.), Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), Association for Computational Linguistics, S. 138–143, doi: 10.18653/v1/2021.textgraphs-1.14.

Details

Author
Steedman, Mark
Title of the compilation
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
Editors
Panchenko, Alexander
Malliaros, Fragkiskos D.
Logacheva, Varvara
Abhik, Jana
Ustalov, Dmitry
Jansen, Peter
Conference
Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), Mexico City, Mexico
Publisher Information
Association for Computational Linguistics
Year of publication
2021
Language
English
DOI
Abstract

Fine-grained entity typing is important to tasks like relation extraction and knowledge base construction. We find however, that fine-grained entity typing systems perform poorly on general entities (e.g. “ex-president”) as compared to named entities (e.g. “Barack Obama”). This is due to a lack of general entities in existing training data sets. We show that this problem can be mitigated by automatically generating training data from WordNets. We use a German WordNet equivalent, GermaNet, to automatically generate training data for German general entity typing. We use this data to supplement named entity data to train a neural fine-grained entity typing system. This leads to a 10% improvement in accuracy of the prediction of level 1 FIGER types for German general entities, while decreasing named entity type prediction accuracy by only 1%.

Keywords
GermaNet
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2024-08-12

Permalink: https://fis.uni-bamberg.de/handle/uniba/97225 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.