@inproceedings{fischer-etal-2016-orthographic,
title = "Orthographic and Morphological Correspondences between Related {S}lavic Languages as a Base for Modeling of Mutual Intelligibility",
author = "Fischer, Andrea and
J{\'a}grov{\'a}, Kl{\'a}ra and
Stenger, Irina and
Avgustinova, Tania and
Klakow, Dietrich and
Marti, Roland",
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/L16-1665",
pages = "4202--4209",
abstract = "In an intercomprehension scenario, typically a native speaker of language L1 is confronted with output from an unknown, but related language L2. In this setting, the degree to which the receiver recognizes the unfamiliar words greatly determines communicative success. Despite exhibiting great string-level differences, cognates may be recognized very successfully if the receiver is aware of regular correspondences which allow to transform the unknown word into its familiar form. Modeling L1-L2 intercomprehension then requires the identification of all the regular correspondences between languages L1 and L2. We here present a set of linguistic orthographic correspondences manually compiled from comparative linguistics literature along with a set of statistically-inferred suggestions for correspondence rules. In order to do statistical inference, we followed the Minimum Description Length principle, which proposes to choose those rules which are most effective at describing the data. Our statistical model was able to reproduce most of our linguistic correspondences (88.5{\%} for Czech-Polish and 75.7{\%} for Bulgarian-Russian) and furthermore allowed to easily identify many more non-trivial correspondences which also cover aspects of morphology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fischer-etal-2016-orthographic">
<titleInfo>
<title>Orthographic and Morphological Correspondences between Related Slavic Languages as a Base for Modeling of Mutual Intelligibility</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Fischer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Klára</namePart>
<namePart type="family">Jágrová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Stenger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Avgustinova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Marti</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 an intercomprehension scenario, typically a native speaker of language L1 is confronted with output from an unknown, but related language L2. In this setting, the degree to which the receiver recognizes the unfamiliar words greatly determines communicative success. Despite exhibiting great string-level differences, cognates may be recognized very successfully if the receiver is aware of regular correspondences which allow to transform the unknown word into its familiar form. Modeling L1-L2 intercomprehension then requires the identification of all the regular correspondences between languages L1 and L2. We here present a set of linguistic orthographic correspondences manually compiled from comparative linguistics literature along with a set of statistically-inferred suggestions for correspondence rules. In order to do statistical inference, we followed the Minimum Description Length principle, which proposes to choose those rules which are most effective at describing the data. Our statistical model was able to reproduce most of our linguistic correspondences (88.5% for Czech-Polish and 75.7% for Bulgarian-Russian) and furthermore allowed to easily identify many more non-trivial correspondences which also cover aspects of morphology.</abstract>
<identifier type="citekey">fischer-etal-2016-orthographic</identifier>
<location>
<url>https://aclanthology.org/L16-1665</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4202</start>
<end>4209</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Orthographic and Morphological Correspondences between Related Slavic Languages as a Base for Modeling of Mutual Intelligibility
%A Fischer, Andrea
%A Jágrová, Klára
%A Stenger, Irina
%A Avgustinova, Tania
%A Klakow, Dietrich
%A Marti, Roland
%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 fischer-etal-2016-orthographic
%X In an intercomprehension scenario, typically a native speaker of language L1 is confronted with output from an unknown, but related language L2. In this setting, the degree to which the receiver recognizes the unfamiliar words greatly determines communicative success. Despite exhibiting great string-level differences, cognates may be recognized very successfully if the receiver is aware of regular correspondences which allow to transform the unknown word into its familiar form. Modeling L1-L2 intercomprehension then requires the identification of all the regular correspondences between languages L1 and L2. We here present a set of linguistic orthographic correspondences manually compiled from comparative linguistics literature along with a set of statistically-inferred suggestions for correspondence rules. In order to do statistical inference, we followed the Minimum Description Length principle, which proposes to choose those rules which are most effective at describing the data. Our statistical model was able to reproduce most of our linguistic correspondences (88.5% for Czech-Polish and 75.7% for Bulgarian-Russian) and furthermore allowed to easily identify many more non-trivial correspondences which also cover aspects of morphology.
%U https://aclanthology.org/L16-1665
%P 4202-4209
Markdown (Informal)
[Orthographic and Morphological Correspondences between Related Slavic Languages as a Base for Modeling of Mutual Intelligibility](https://aclanthology.org/L16-1665) (Fischer et al., LREC 2016)
ACL