@inproceedings{brandsen-etal-2020-creating,
title = "Creating a Dataset for Named Entity Recognition in the Archaeology Domain",
author = "Brandsen, Alex and
Verberne, Suzan and
Wansleeben, Milco and
Lambers, Karsten",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.562",
pages = "4573--4577",
abstract = "In this paper, we present the development of a training dataset for Dutch Named Entity Recognition (NER) in the archaeology domain. This dataset was created as there is a dire need for semantic search within archaeology, in order to allow archaeologists to find structured information in collections of Dutch excavation reports, currently totalling around 60,000 (658 million words) and growing rapidly. To guide this search task, NER is needed. We created rigorous annotation guidelines in an iterative process, then instructed five archaeology students to annotate a number of documents. The resulting dataset contains {\textasciitilde}31k annotations between six entity types (artefact, time period, place, context, species {\&} material). The inter-annotator agreement is 0.95, and when we used this data for machine learning, we observed an increase in F1 score from 0.51 to 0.70 in comparison to a machine learning model trained on a dataset created in prior work. This indicates that the data is of high quality, and can confidently be used to train NER classifiers.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brandsen-etal-2020-creating">
<titleInfo>
<title>Creating a Dataset for Named Entity Recognition in the Archaeology Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Brandsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzan</namePart>
<namePart type="family">Verberne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milco</namePart>
<namePart type="family">Wansleeben</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karsten</namePart>
<namePart type="family">Lambers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we present the development of a training dataset for Dutch Named Entity Recognition (NER) in the archaeology domain. This dataset was created as there is a dire need for semantic search within archaeology, in order to allow archaeologists to find structured information in collections of Dutch excavation reports, currently totalling around 60,000 (658 million words) and growing rapidly. To guide this search task, NER is needed. We created rigorous annotation guidelines in an iterative process, then instructed five archaeology students to annotate a number of documents. The resulting dataset contains ~31k annotations between six entity types (artefact, time period, place, context, species & material). The inter-annotator agreement is 0.95, and when we used this data for machine learning, we observed an increase in F1 score from 0.51 to 0.70 in comparison to a machine learning model trained on a dataset created in prior work. This indicates that the data is of high quality, and can confidently be used to train NER classifiers.</abstract>
<identifier type="citekey">brandsen-etal-2020-creating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.562</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4573</start>
<end>4577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Dataset for Named Entity Recognition in the Archaeology Domain
%A Brandsen, Alex
%A Verberne, Suzan
%A Wansleeben, Milco
%A Lambers, Karsten
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F brandsen-etal-2020-creating
%X In this paper, we present the development of a training dataset for Dutch Named Entity Recognition (NER) in the archaeology domain. This dataset was created as there is a dire need for semantic search within archaeology, in order to allow archaeologists to find structured information in collections of Dutch excavation reports, currently totalling around 60,000 (658 million words) and growing rapidly. To guide this search task, NER is needed. We created rigorous annotation guidelines in an iterative process, then instructed five archaeology students to annotate a number of documents. The resulting dataset contains ~31k annotations between six entity types (artefact, time period, place, context, species & material). The inter-annotator agreement is 0.95, and when we used this data for machine learning, we observed an increase in F1 score from 0.51 to 0.70 in comparison to a machine learning model trained on a dataset created in prior work. This indicates that the data is of high quality, and can confidently be used to train NER classifiers.
%U https://aclanthology.org/2020.lrec-1.562
%P 4573-4577
Markdown (Informal)
[Creating a Dataset for Named Entity Recognition in the Archaeology Domain](https://aclanthology.org/2020.lrec-1.562) (Brandsen et al., LREC 2020)
ACL