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
- Autorin(nen)/Autor(en)
- Steedman, Mark
- Titel des Sammelwerks
- Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
- Herausgeberin(nen)/Herausgeber des Sammelwerks
- Panchenko, AlexanderMalliaros, Fragkiskos D.Logacheva, VarvaraAbhik, JanaUstalov, DmitryJansen, Peter
- Konferenz
- Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), Mexico City, Mexico
- Verlagsangabe
- Association for Computational Linguistics
- Erscheinungsjahr
- 2021
- Sprache(n)
- Englisch
- 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%.
- Freie Schlagwort(e)
- GermaNet
- Peer Reviewed
- ja
- Internationale Verbreitung
- ja
- Open-Access-Zeitschrift
- ja
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 12.08.2024