@inproceedings{knyazeva-etal-2022-aesops,
title = "{A}esop{'}s fable {``}The North Wind and the Sun{''} Used as a Rosetta Stone to Extract and Map Spoken Words in Under-resourced Languages",
author = {Knyazeva, Elena and
Boula de Mare{\"u}il, Philippe and
Vernier, Fr{\'e}d{\'e}ric},
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-1.223",
pages = "2072--2079",
abstract = "This paper describes a method of semi-automatic word spotting in minority languages, from one and the same Aesop fable {``}The North Wind and the Sun{''} translated in Romance languages/dialects from Hexagonal (i.e. Metropolitan) France and languages from French Polynesia. The first task consisted of finding out how a dozen words such as {``}wind{''} and {``}sun{''} were translated in over 200 versions collected in the field {---} taking advantage of orthographic similarity, word position and context. Occurrences of the translations were then extracted from the phone-aligned recordings. The results were judged accurate in 96{--}97{\%} of cases, both on the development corpus and a test set of unseen data. Corrected alignments were then mapped and basemaps were drawn to make various linguistic phenomena immediately visible. The paper exemplifies how regular expressions may be used for this purpose. The final result, which takes the form of an online speaking atlas (enriching the \url{https://atlas.limsi.fr} website), enables us to illustrate lexical, morphological or phonetic variation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="knyazeva-etal-2022-aesops">
<titleInfo>
<title>Aesop’s fable “The North Wind and the Sun” Used as a Rosetta Stone to Extract and Map Spoken Words in Under-resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Knyazeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Boula de Mareüil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Vernier</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>This paper describes a method of semi-automatic word spotting in minority languages, from one and the same Aesop fable “The North Wind and the Sun” translated in Romance languages/dialects from Hexagonal (i.e. Metropolitan) France and languages from French Polynesia. The first task consisted of finding out how a dozen words such as “wind” and “sun” were translated in over 200 versions collected in the field — taking advantage of orthographic similarity, word position and context. Occurrences of the translations were then extracted from the phone-aligned recordings. The results were judged accurate in 96–97% of cases, both on the development corpus and a test set of unseen data. Corrected alignments were then mapped and basemaps were drawn to make various linguistic phenomena immediately visible. The paper exemplifies how regular expressions may be used for this purpose. The final result, which takes the form of an online speaking atlas (enriching the https://atlas.limsi.fr website), enables us to illustrate lexical, morphological or phonetic variation.</abstract>
<identifier type="citekey">knyazeva-etal-2022-aesops</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.223</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2072</start>
<end>2079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aesop’s fable “The North Wind and the Sun” Used as a Rosetta Stone to Extract and Map Spoken Words in Under-resourced Languages
%A Knyazeva, Elena
%A Boula de Mareüil, Philippe
%A Vernier, Frédéric
%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 knyazeva-etal-2022-aesops
%X This paper describes a method of semi-automatic word spotting in minority languages, from one and the same Aesop fable “The North Wind and the Sun” translated in Romance languages/dialects from Hexagonal (i.e. Metropolitan) France and languages from French Polynesia. The first task consisted of finding out how a dozen words such as “wind” and “sun” were translated in over 200 versions collected in the field — taking advantage of orthographic similarity, word position and context. Occurrences of the translations were then extracted from the phone-aligned recordings. The results were judged accurate in 96–97% of cases, both on the development corpus and a test set of unseen data. Corrected alignments were then mapped and basemaps were drawn to make various linguistic phenomena immediately visible. The paper exemplifies how regular expressions may be used for this purpose. The final result, which takes the form of an online speaking atlas (enriching the https://atlas.limsi.fr website), enables us to illustrate lexical, morphological or phonetic variation.
%U https://aclanthology.org/2022.lrec-1.223
%P 2072-2079
Markdown (Informal)
[Aesop’s fable “The North Wind and the Sun” Used as a Rosetta Stone to Extract and Map Spoken Words in Under-resourced Languages](https://aclanthology.org/2022.lrec-1.223) (Knyazeva et al., LREC 2022)
ACL