@inproceedings{ahmed-etal-2019-biofid,
title = "{BIO}fid Dataset: Publishing a {G}erman Gold Standard for Named Entity Recognition in Historical Biodiversity Literature",
author = "Ahmed, Sajawel and
Stoeckel, Manuel and
Driller, Christine and
Pachzelt, Adrian and
Mehler, Alexander",
editor = "Bansal, Mohit and
Villavicencio, Aline",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1081",
doi = "10.18653/v1/K19-1081",
pages = "871--880",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmed-etal-2019-biofid">
<titleInfo>
<title>BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sajawel</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Stoeckel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Driller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Pachzelt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Mehler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">ahmed-etal-2019-biofid</identifier>
<identifier type="doi">10.18653/v1/K19-1081</identifier>
<location>
<url>https://aclanthology.org/K19-1081</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>871</start>
<end>880</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature
%A Ahmed, Sajawel
%A Stoeckel, Manuel
%A Driller, Christine
%A Pachzelt, Adrian
%A Mehler, Alexander
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ahmed-etal-2019-biofid
%X 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.
%R 10.18653/v1/K19-1081
%U https://aclanthology.org/K19-1081
%U https://doi.org/10.18653/v1/K19-1081
%P 871-880
Markdown (Informal)
[BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature](https://aclanthology.org/K19-1081) (Ahmed et al., CoNLL 2019)
ACL