@inproceedings{erdmann-etal-2016-challenges,
title = "Challenges and Solutions for {L}atin Named Entity Recognition",
author = "Erdmann, Alexander and
Brown, Christopher and
Joseph, Brian and
Janse, Mark and
Ajaka, Petra and
Elsner, Micha and
de Marneffe, Marie-Catherine",
editor = "Hinrichs, Erhard and
Hinrichs, Marie and
Trippel, Thorsten",
booktitle = "Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities ({LT}4{DH})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4012",
pages = "85--93",
abstract = "Although spanning thousands of years and genres as diverse as liturgy, historiography, lyric and other forms of prose and poetry, the body of Latin texts is still relatively sparse compared to English. Data sparsity in Latin presents a number of challenges for traditional Named Entity Recognition techniques. Solving such challenges and enabling reliable Named Entity Recognition in Latin texts can facilitate many down-stream applications, from machine translation to digital historiography, enabling Classicists, historians, and archaeologists for instance, to track the relationships of historical persons, places, and groups on a large scale. This paper presents the first annotated corpus for evaluating Named Entity Recognition in Latin, as well as a fully supervised model that achieves over 90{\%} F-score on a held-out test set, significantly outperforming a competitive baseline. We also present a novel active learning strategy that predicts how many and which sentences need to be annotated for named entities in order to attain a specified degree of accuracy when recognizing named entities automatically in a given text. This maximizes the productivity of annotators while simultaneously controlling quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erdmann-etal-2016-challenges">
<titleInfo>
<title>Challenges and Solutions for Latin Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Erdmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Joseph</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Janse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petra</namePart>
<namePart type="family">Ajaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micha</namePart>
<namePart type="family">Elsner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erhard</namePart>
<namePart type="family">Hinrichs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Hinrichs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thorsten</namePart>
<namePart type="family">Trippel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although spanning thousands of years and genres as diverse as liturgy, historiography, lyric and other forms of prose and poetry, the body of Latin texts is still relatively sparse compared to English. Data sparsity in Latin presents a number of challenges for traditional Named Entity Recognition techniques. Solving such challenges and enabling reliable Named Entity Recognition in Latin texts can facilitate many down-stream applications, from machine translation to digital historiography, enabling Classicists, historians, and archaeologists for instance, to track the relationships of historical persons, places, and groups on a large scale. This paper presents the first annotated corpus for evaluating Named Entity Recognition in Latin, as well as a fully supervised model that achieves over 90% F-score on a held-out test set, significantly outperforming a competitive baseline. We also present a novel active learning strategy that predicts how many and which sentences need to be annotated for named entities in order to attain a specified degree of accuracy when recognizing named entities automatically in a given text. This maximizes the productivity of annotators while simultaneously controlling quality.</abstract>
<identifier type="citekey">erdmann-etal-2016-challenges</identifier>
<location>
<url>https://aclanthology.org/W16-4012</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>85</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenges and Solutions for Latin Named Entity Recognition
%A Erdmann, Alexander
%A Brown, Christopher
%A Joseph, Brian
%A Janse, Mark
%A Ajaka, Petra
%A Elsner, Micha
%A de Marneffe, Marie-Catherine
%Y Hinrichs, Erhard
%Y Hinrichs, Marie
%Y Trippel, Thorsten
%S Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F erdmann-etal-2016-challenges
%X Although spanning thousands of years and genres as diverse as liturgy, historiography, lyric and other forms of prose and poetry, the body of Latin texts is still relatively sparse compared to English. Data sparsity in Latin presents a number of challenges for traditional Named Entity Recognition techniques. Solving such challenges and enabling reliable Named Entity Recognition in Latin texts can facilitate many down-stream applications, from machine translation to digital historiography, enabling Classicists, historians, and archaeologists for instance, to track the relationships of historical persons, places, and groups on a large scale. This paper presents the first annotated corpus for evaluating Named Entity Recognition in Latin, as well as a fully supervised model that achieves over 90% F-score on a held-out test set, significantly outperforming a competitive baseline. We also present a novel active learning strategy that predicts how many and which sentences need to be annotated for named entities in order to attain a specified degree of accuracy when recognizing named entities automatically in a given text. This maximizes the productivity of annotators while simultaneously controlling quality.
%U https://aclanthology.org/W16-4012
%P 85-93
Markdown (Informal)
[Challenges and Solutions for Latin Named Entity Recognition](https://aclanthology.org/W16-4012) (Erdmann et al., LT4DH 2016)
ACL
- Alexander Erdmann, Christopher Brown, Brian Joseph, Mark Janse, Petra Ajaka, Micha Elsner, and Marie-Catherine de Marneffe. 2016. Challenges and Solutions for Latin Named Entity Recognition. In Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH), pages 85–93, Osaka, Japan. The COLING 2016 Organizing Committee.