@inproceedings{hupkes-bod-2016-pos,
title = "{POS}-tagging of Historical {D}utch",
author = "Hupkes, Dieuwke and
Bod, Rens",
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/L16-1012",
pages = "77--82",
abstract = "We present a study of the adequacy of current methods that are used for POS-tagging historical Dutch texts, as well as an exploration of the influence of employing different techniques to improve upon the current practice. The main focus of this paper is on (unsupervised) methods that are easily adaptable for different domains without requiring extensive manual input. It was found that modernising the spelling of corpora prior to tagging them with a tagger trained on contemporary Dutch results in a large increase in accuracy, but that spelling normalisation alone is not sufficient to obtain state-of-the-art results. The best results were achieved by training a POS-tagger on a corpus automatically annotated by projecting (automatically assigned) POS-tags via word alignments from a contemporary corpus. This result is promising, as it was reached without including any domain knowledge or context dependencies. We argue that the insights of this study combined with semi-supervised learning techniques for domain adaptation can be used to develop a general-purpose diachronic tagger for Dutch.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hupkes-bod-2016-pos">
<titleInfo>
<title>POS-tagging of Historical Dutch</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rens</namePart>
<namePart type="family">Bod</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>We present a study of the adequacy of current methods that are used for POS-tagging historical Dutch texts, as well as an exploration of the influence of employing different techniques to improve upon the current practice. The main focus of this paper is on (unsupervised) methods that are easily adaptable for different domains without requiring extensive manual input. It was found that modernising the spelling of corpora prior to tagging them with a tagger trained on contemporary Dutch results in a large increase in accuracy, but that spelling normalisation alone is not sufficient to obtain state-of-the-art results. The best results were achieved by training a POS-tagger on a corpus automatically annotated by projecting (automatically assigned) POS-tags via word alignments from a contemporary corpus. This result is promising, as it was reached without including any domain knowledge or context dependencies. We argue that the insights of this study combined with semi-supervised learning techniques for domain adaptation can be used to develop a general-purpose diachronic tagger for Dutch.</abstract>
<identifier type="citekey">hupkes-bod-2016-pos</identifier>
<location>
<url>https://aclanthology.org/L16-1012</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>77</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T POS-tagging of Historical Dutch
%A Hupkes, Dieuwke
%A Bod, Rens
%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 hupkes-bod-2016-pos
%X We present a study of the adequacy of current methods that are used for POS-tagging historical Dutch texts, as well as an exploration of the influence of employing different techniques to improve upon the current practice. The main focus of this paper is on (unsupervised) methods that are easily adaptable for different domains without requiring extensive manual input. It was found that modernising the spelling of corpora prior to tagging them with a tagger trained on contemporary Dutch results in a large increase in accuracy, but that spelling normalisation alone is not sufficient to obtain state-of-the-art results. The best results were achieved by training a POS-tagger on a corpus automatically annotated by projecting (automatically assigned) POS-tags via word alignments from a contemporary corpus. This result is promising, as it was reached without including any domain knowledge or context dependencies. We argue that the insights of this study combined with semi-supervised learning techniques for domain adaptation can be used to develop a general-purpose diachronic tagger for Dutch.
%U https://aclanthology.org/L16-1012
%P 77-82
Markdown (Informal)
[POS-tagging of Historical Dutch](https://aclanthology.org/L16-1012) (Hupkes & Bod, LREC 2016)
ACL
- Dieuwke Hupkes and Rens Bod. 2016. POS-tagging of Historical Dutch. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 77–82, Portorož, Slovenia. European Language Resources Association (ELRA).