@inproceedings{sanchez-marco-etal-2010-annotation,
title = "Annotation and Representation of a Diachronic Corpus of {S}panish",
author = "S{\'a}nchez-Marco, Cristina and
Boleda, Gemma and
Fontana, Josep Maria and
Domingo, Judith",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}`10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L10-1368/",
abstract = "In this article we describe two different strategies for the automatic tagging of a Spanish diachronic corpus involving the adaptation of existing NLP tools developed for modern Spanish. In the initial approach we follow a state-of-the-art strategy, which consists on standardizing the spelling and the lexicon. This approach boosts POS-tagging accuracy to 90, which represents a raw improvement of over 20{\%} with respect to the results obtained without any pre-processing. In order to enable non-expert users in NLP to use this new resource, the corpus has been integrated into IAC (Corpora Interface Access). We discuss the shortcomings of the initial approach and propose a new one, which does not consist in adapting the source texts to the tagger, but rather in modifying the tagger for the direct treatment of the old variants. This second strategy addresses some important shortcomings in the previous approach and is likely to be useful not only in the creation of diachronic linguistic resources but also for the treatment of dialectal or non-standard variants of synchronic languages as well."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-marco-etal-2010-annotation">
<titleInfo>
<title>Annotation and Representation of a Diachronic Corpus of Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Sánchez-Marco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Boleda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Fontana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Domingo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this article we describe two different strategies for the automatic tagging of a Spanish diachronic corpus involving the adaptation of existing NLP tools developed for modern Spanish. In the initial approach we follow a state-of-the-art strategy, which consists on standardizing the spelling and the lexicon. This approach boosts POS-tagging accuracy to 90, which represents a raw improvement of over 20% with respect to the results obtained without any pre-processing. In order to enable non-expert users in NLP to use this new resource, the corpus has been integrated into IAC (Corpora Interface Access). We discuss the shortcomings of the initial approach and propose a new one, which does not consist in adapting the source texts to the tagger, but rather in modifying the tagger for the direct treatment of the old variants. This second strategy addresses some important shortcomings in the previous approach and is likely to be useful not only in the creation of diachronic linguistic resources but also for the treatment of dialectal or non-standard variants of synchronic languages as well.</abstract>
<identifier type="citekey">sanchez-marco-etal-2010-annotation</identifier>
<location>
<url>https://aclanthology.org/L10-1368/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotation and Representation of a Diachronic Corpus of Spanish
%A Sánchez-Marco, Cristina
%A Boleda, Gemma
%A Fontana, Josep Maria
%A Domingo, Judith
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F sanchez-marco-etal-2010-annotation
%X In this article we describe two different strategies for the automatic tagging of a Spanish diachronic corpus involving the adaptation of existing NLP tools developed for modern Spanish. In the initial approach we follow a state-of-the-art strategy, which consists on standardizing the spelling and the lexicon. This approach boosts POS-tagging accuracy to 90, which represents a raw improvement of over 20% with respect to the results obtained without any pre-processing. In order to enable non-expert users in NLP to use this new resource, the corpus has been integrated into IAC (Corpora Interface Access). We discuss the shortcomings of the initial approach and propose a new one, which does not consist in adapting the source texts to the tagger, but rather in modifying the tagger for the direct treatment of the old variants. This second strategy addresses some important shortcomings in the previous approach and is likely to be useful not only in the creation of diachronic linguistic resources but also for the treatment of dialectal or non-standard variants of synchronic languages as well.
%U https://aclanthology.org/L10-1368/
Markdown (Informal)
[Annotation and Representation of a Diachronic Corpus of Spanish](https://aclanthology.org/L10-1368/) (Sánchez-Marco et al., LREC 2010)
ACL
- Cristina Sánchez-Marco, Gemma Boleda, Josep Maria Fontana, and Judith Domingo. 2010. Annotation and Representation of a Diachronic Corpus of Spanish. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).