Title
TSE-NER: An Iterative Approach for Long-Tail Entity Extraction in Scientific Publications
Author
Mesbah, S. (TU Delft Web Information Systems)
Lofi, C. (TU Delft Web Information Systems)
Valle Torre, M. (TU Delft Web Information Systems)
Bozzon, A. (TU Delft Web Information Systems)
Houben, G.J.P.M. (TU Delft Web Information Systems)
Contributor
Vrandečić, D. (editor)
Bontcheva, K. (editor)
Suárez-Figueroa, M.C. (editor)
Presutti, V. (editor)
Celino, I. (editor)
Sabou, M. (editor)
Kaffee, L.M (editor)
Simperl, E. (editor)
Date
2018
Abstract
Named Entity Recognition and Typing (NER/NET) is a challenging task, especially with long-tail entities such as the ones found in scientific publications. These entities (e.g. “WebKB”, “StatSnowball”) are rare, often relevant only in specific knowledge domains, yet important for retrieval and exploration purposes. State-of-the-art NER approaches employ supervised machine learning models, trained on expensive typelabeled data laboriously produced by human annotators. A common workaround is the generation of labeled training data from knowledge bases; this approach is not suitable for long-tail entity types that are, by definition, scarcely represented in KBs.
This paper presents an iterative approach for training NER and NET
classifiers in scientific publications that relies on minimal human input,
namely a small seed set of instances for the targeted entity type. We
introduce different strategies for training data extraction, semantic expansion, and result entity filtering.We evaluate our approach on scientific
publications, focusing on the long-tail entities types Datasets, Methods in
computer science publications, and Proteins in biomedical publications.
To reference this document use:
http://resolver.tudelft.nl/uuid:91b0bf60-1304-4b2f-ba55-f58f04351381
DOI
https://doi.org/10.1007/978-3-030-00671-6_8
Publisher
Springer, Cham
Embargo date
2019-02-18
ISBN
978-3-030-00670-9
Source
The Semantic Web – ISWC 2018: Proceedings of the 17th International Semantic Web Conference
Event
ISWC 2018, 2018-10-08 → 2018-10-12, Monterey, CA, United States
Series
Lecture Notes in Computer Science (LNCS), 11136
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
conference paper
Rights
© 2018 S. Mesbah, C. Lofi, M. Valle Torre, A. Bozzon, G.J.P.M. Houben