BIOfid dataset: publishing a German gold standard for named entity recognition in historical biodiversity literature

  • The Specialized Information Service Biodiversity Research (BIOfid) has been launched to mobilize valuable biological data from printed literature hidden in German libraries for over the past 250 years. In this project, we annotate German texts converted by OCR from historical scientific literature on the biodiversity of plants, birds, moths and butterflies. Our work enables the automatic extraction of biological information previously buried in the mass of papers and volumes. For this purpose, we generated training data for the tasks of Named Entity Recognition (NER) and Taxa Recognition (TR) in biological documents. We use this data to train a number of leading machine learning tools and create a gold standard for TR in biodiversity literature. More specifically, we perform a practical analysis of our newly generated BIOfid dataset through various downstream-task evaluations and establish a new state of the art for TR with 80.23% F-score. In this sense, our paper lays the foundations for future work in the field of information extraction in biology texts.

Download full text files

Export metadata

Author:Sajawel Ahmed, Manuel Stoeckel, Christine DrillerORCiDGND, Adrian PachzeltORCiDGND, Alexander MehlerORCiDGND
Parent Title (German):Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Hong Kong, November 3-4, 2019
Publisher:Association for Computational Linguistics
Place of publication:[Erscheinungsort nicht ermittelbar]
Document Type:Conference Proceeding
Year of Completion:2019
Year of first Publication:2019
Publishing Institution:Universit├Ątsbibliothek Johann Christian Senckenberg
Release Date:2022/05/06
Page Number:10
First Page:871
Last Page:880
Institutes:Informatik und Mathematik / Informatik
Zentrale Einrichtung / Universit├Ątsbibliothek
Angeschlossene und kooperierende Institutionen / Senckenbergische Naturforschende Gesellschaft
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 02 Bibliotheks- und Informationswissenschaften / 020 Bibliotheks- und Informationswissenschaften
5 Naturwissenschaften und Mathematik / 57 Biowissenschaften; Biologie / 570 Biowissenschaften; Biologie
Sammlung Biologie / Sondersammelgebiets-Volltexte
Licence (German):License LogoCreative Commons - Namensnennung 4.0