@inproceedings{chiarcos-etal-2022-querying,
title = "Querying a Dozen Corpora and a Thousand Years with Fintan",
author = {Chiarcos, Christian and
F{\"a}th, Christian and
Ionov, Maxim},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.427",
pages = "4011--4021",
abstract = "Large-scale diachronic corpus studies covering longer time periods are difficult if more than one corpus are to be consulted and, as a result, different formats and annotation schemas need to be processed and queried in a uniform, comparable and replicable manner. We describes the application of the Flexible Integrated Transformation and Annotation eNgineering (Fintan) platform for studying word order in German using syntactically annotated corpora that represent its entire written history. Focusing on nominal dative and accusative arguments, this study hints at two major phases in the development of scrambling in modern German. Against more recent assumptions, it supports the traditional view that word order flexibility decreased over time, but it also indicates that this was a relatively sharp transition in Early New High German. The successful case study demonstrates the potential of Fintan and the underlying LLOD technology for historical linguistics, linguistic typology and corpus linguistics. The technological contribution of this paper is to demonstrate the applicability of Fintan for querying across heterogeneously annotated corpora, as previously, it had only been applied for transformation tasks. With its focus on quantitative analysis, Fintan is a natural complement for existing multi-layer technologies that focus on query and exploration.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiarcos-etal-2022-querying">
<titleInfo>
<title>Querying a Dozen Corpora and a Thousand Years with Fintan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Chiarcos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Fäth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale diachronic corpus studies covering longer time periods are difficult if more than one corpus are to be consulted and, as a result, different formats and annotation schemas need to be processed and queried in a uniform, comparable and replicable manner. We describes the application of the Flexible Integrated Transformation and Annotation eNgineering (Fintan) platform for studying word order in German using syntactically annotated corpora that represent its entire written history. Focusing on nominal dative and accusative arguments, this study hints at two major phases in the development of scrambling in modern German. Against more recent assumptions, it supports the traditional view that word order flexibility decreased over time, but it also indicates that this was a relatively sharp transition in Early New High German. The successful case study demonstrates the potential of Fintan and the underlying LLOD technology for historical linguistics, linguistic typology and corpus linguistics. The technological contribution of this paper is to demonstrate the applicability of Fintan for querying across heterogeneously annotated corpora, as previously, it had only been applied for transformation tasks. With its focus on quantitative analysis, Fintan is a natural complement for existing multi-layer technologies that focus on query and exploration.</abstract>
<identifier type="citekey">chiarcos-etal-2022-querying</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.427</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4011</start>
<end>4021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Querying a Dozen Corpora and a Thousand Years with Fintan
%A Chiarcos, Christian
%A Fäth, Christian
%A Ionov, Maxim
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F chiarcos-etal-2022-querying
%X Large-scale diachronic corpus studies covering longer time periods are difficult if more than one corpus are to be consulted and, as a result, different formats and annotation schemas need to be processed and queried in a uniform, comparable and replicable manner. We describes the application of the Flexible Integrated Transformation and Annotation eNgineering (Fintan) platform for studying word order in German using syntactically annotated corpora that represent its entire written history. Focusing on nominal dative and accusative arguments, this study hints at two major phases in the development of scrambling in modern German. Against more recent assumptions, it supports the traditional view that word order flexibility decreased over time, but it also indicates that this was a relatively sharp transition in Early New High German. The successful case study demonstrates the potential of Fintan and the underlying LLOD technology for historical linguistics, linguistic typology and corpus linguistics. The technological contribution of this paper is to demonstrate the applicability of Fintan for querying across heterogeneously annotated corpora, as previously, it had only been applied for transformation tasks. With its focus on quantitative analysis, Fintan is a natural complement for existing multi-layer technologies that focus on query and exploration.
%U https://aclanthology.org/2022.lrec-1.427
%P 4011-4021
Markdown (Informal)
[Querying a Dozen Corpora and a Thousand Years with Fintan](https://aclanthology.org/2022.lrec-1.427) (Chiarcos et al., LREC 2022)
ACL