@inproceedings{mambrini-passarotti-2019-harmonizing,
title = "Harmonizing Different Lemmatization Strategies for Building a Knowledge Base of Linguistic Resources for {L}atin",
author = "Mambrini, Francesco and
Passarotti, Marco",
editor = "Friedrich, Annemarie and
Zeyrek, Deniz and
Hoek, Jet",
booktitle = "Proceedings of the 13th Linguistic Annotation Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4009",
doi = "10.18653/v1/W19-4009",
pages = "71--80",
abstract = "The interoperability between lemmatized corpora of Latin and other resources that use the lemma as indexing key is hampered by the multiple lemmatization strategies that different projects adopt. In this paper we discuss how we tackle the challenges raised by harmonizing different lemmatization criteria in the context of a project that aims to connect linguistic resources for Latin using the Linked Data paradigm. The paper introduces the architecture supporting an open-ended, lemma-based Knowledge Base, built to make textual and lexical resources for Latin interoperable. Particularly, the paper describes the inclusion into the Knowledge Base of its lexical basis, of a word formation lexicon and of a lemmatized and syntactically annotated corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mambrini-passarotti-2019-harmonizing">
<titleInfo>
<title>Harmonizing Different Lemmatization Strategies for Building a Knowledge Base of Linguistic Resources for Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Mambrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Linguistic Annotation Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deniz</namePart>
<namePart type="family">Zeyrek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jet</namePart>
<namePart type="family">Hoek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The interoperability between lemmatized corpora of Latin and other resources that use the lemma as indexing key is hampered by the multiple lemmatization strategies that different projects adopt. In this paper we discuss how we tackle the challenges raised by harmonizing different lemmatization criteria in the context of a project that aims to connect linguistic resources for Latin using the Linked Data paradigm. The paper introduces the architecture supporting an open-ended, lemma-based Knowledge Base, built to make textual and lexical resources for Latin interoperable. Particularly, the paper describes the inclusion into the Knowledge Base of its lexical basis, of a word formation lexicon and of a lemmatized and syntactically annotated corpus.</abstract>
<identifier type="citekey">mambrini-passarotti-2019-harmonizing</identifier>
<identifier type="doi">10.18653/v1/W19-4009</identifier>
<location>
<url>https://aclanthology.org/W19-4009</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>71</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Harmonizing Different Lemmatization Strategies for Building a Knowledge Base of Linguistic Resources for Latin
%A Mambrini, Francesco
%A Passarotti, Marco
%Y Friedrich, Annemarie
%Y Zeyrek, Deniz
%Y Hoek, Jet
%S Proceedings of the 13th Linguistic Annotation Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F mambrini-passarotti-2019-harmonizing
%X The interoperability between lemmatized corpora of Latin and other resources that use the lemma as indexing key is hampered by the multiple lemmatization strategies that different projects adopt. In this paper we discuss how we tackle the challenges raised by harmonizing different lemmatization criteria in the context of a project that aims to connect linguistic resources for Latin using the Linked Data paradigm. The paper introduces the architecture supporting an open-ended, lemma-based Knowledge Base, built to make textual and lexical resources for Latin interoperable. Particularly, the paper describes the inclusion into the Knowledge Base of its lexical basis, of a word formation lexicon and of a lemmatized and syntactically annotated corpus.
%R 10.18653/v1/W19-4009
%U https://aclanthology.org/W19-4009
%U https://doi.org/10.18653/v1/W19-4009
%P 71-80
Markdown (Informal)
[Harmonizing Different Lemmatization Strategies for Building a Knowledge Base of Linguistic Resources for Latin](https://aclanthology.org/W19-4009) (Mambrini & Passarotti, LAW 2019)
ACL