@inproceedings{schulz-kuhn-2016-learning,
title = "Learning from Within? Comparing {P}o{S} Tagging Approaches for Historical Text",
author = "Schulz, Sarah and
Kuhn, Jonas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1684",
pages = "4316--4322",
abstract = "In this paper, we investigate unsupervised and semi-supervised methods for part-of-speech (PoS) tagging in the context of historical German text. We locate our research in the context of Digital Humanities where the non-canonical nature of text causes issues facing an Natural Language Processing world in which tools are mainly trained on standard data. Data deviating from the norm requires tools adjusted to this data. We explore to which extend the availability of such training material and resources related to it influences the accuracy of PoS tagging. We investigate a variety of algorithms including neural nets, conditional random fields and self-learning techniques in order to find the best-fitted approach to tackle data sparsity. Although methods using resources from related languages outperform weakly supervised methods using just a few training examples, we can still reach a promising accuracy with methods abstaining additional resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schulz-kuhn-2016-learning">
<titleInfo>
<title>Learning from Within? Comparing PoS Tagging Approaches for Historical Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we investigate unsupervised and semi-supervised methods for part-of-speech (PoS) tagging in the context of historical German text. We locate our research in the context of Digital Humanities where the non-canonical nature of text causes issues facing an Natural Language Processing world in which tools are mainly trained on standard data. Data deviating from the norm requires tools adjusted to this data. We explore to which extend the availability of such training material and resources related to it influences the accuracy of PoS tagging. We investigate a variety of algorithms including neural nets, conditional random fields and self-learning techniques in order to find the best-fitted approach to tackle data sparsity. Although methods using resources from related languages outperform weakly supervised methods using just a few training examples, we can still reach a promising accuracy with methods abstaining additional resources.</abstract>
<identifier type="citekey">schulz-kuhn-2016-learning</identifier>
<location>
<url>https://aclanthology.org/L16-1684</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4316</start>
<end>4322</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning from Within? Comparing PoS Tagging Approaches for Historical Text
%A Schulz, Sarah
%A Kuhn, Jonas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F schulz-kuhn-2016-learning
%X In this paper, we investigate unsupervised and semi-supervised methods for part-of-speech (PoS) tagging in the context of historical German text. We locate our research in the context of Digital Humanities where the non-canonical nature of text causes issues facing an Natural Language Processing world in which tools are mainly trained on standard data. Data deviating from the norm requires tools adjusted to this data. We explore to which extend the availability of such training material and resources related to it influences the accuracy of PoS tagging. We investigate a variety of algorithms including neural nets, conditional random fields and self-learning techniques in order to find the best-fitted approach to tackle data sparsity. Although methods using resources from related languages outperform weakly supervised methods using just a few training examples, we can still reach a promising accuracy with methods abstaining additional resources.
%U https://aclanthology.org/L16-1684
%P 4316-4322
Markdown (Informal)
[Learning from Within? Comparing PoS Tagging Approaches for Historical Text](https://aclanthology.org/L16-1684) (Schulz & Kuhn, LREC 2016)
ACL