@inproceedings{alnajjar-etal-2022-using,
title = "Using Graph-Based Methods to Augment Online Dictionaries of Endangered Languages",
author = {Alnajjar, Khalid and
H{\"a}m{\"a}l{\"a}inen, Mika and
Tapio Partanen, Niko and
Rueter, Jack},
editor = "Moeller, Sarah and
Anastasopoulos, Antonios and
Arppe, Antti and
Chaudhary, Aditi and
Harrigan, Atticus and
Holden, Josh and
Lachler, Jordan and
Palmer, Alexis and
Rijhwani, Shruti and
Schwartz, Lane",
booktitle = "Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.computel-1.18",
doi = "10.18653/v1/2022.computel-1.18",
pages = "139--148",
abstract = "Many endangered Uralic languages have multilingual machine readable dictionaries saved in an XML format. However, the dictionaries cover translations very inconsistently between language pairs, for instance, the Livonian dictionary has some translations to Finnish, Latvian and Estonian, and the Komi-Zyrian dictionary has some translations to Finnish, English and Russian. We utilize graph-based approaches to augment such dictionaries by predicting new translations to existing and new languages based on different dictionaries for endangered languages and Wiktionaries. Our study focuses on the lexical resources for Komi-Zyrian (kpv), Erzya (myv) and Livonian (liv). We evaluate our approach by human judges fluent in the three endangered languages in question. Based on the evaluation, the method predicted good or acceptable translations 77{\%} of the time. Furthermore, we train a neural prediction model to predict the quality of the automatically predicted translations with an 81{\%} accuracy. The resulting extensions to the dictionaries are made available on the online dictionary platform used by the speakers of these languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alnajjar-etal-2022-using">
<titleInfo>
<title>Using Graph-Based Methods to Augment Online Dictionaries of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Tapio Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atticus</namePart>
<namePart type="family">Harrigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Holden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Lachler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many endangered Uralic languages have multilingual machine readable dictionaries saved in an XML format. However, the dictionaries cover translations very inconsistently between language pairs, for instance, the Livonian dictionary has some translations to Finnish, Latvian and Estonian, and the Komi-Zyrian dictionary has some translations to Finnish, English and Russian. We utilize graph-based approaches to augment such dictionaries by predicting new translations to existing and new languages based on different dictionaries for endangered languages and Wiktionaries. Our study focuses on the lexical resources for Komi-Zyrian (kpv), Erzya (myv) and Livonian (liv). We evaluate our approach by human judges fluent in the three endangered languages in question. Based on the evaluation, the method predicted good or acceptable translations 77% of the time. Furthermore, we train a neural prediction model to predict the quality of the automatically predicted translations with an 81% accuracy. The resulting extensions to the dictionaries are made available on the online dictionary platform used by the speakers of these languages.</abstract>
<identifier type="citekey">alnajjar-etal-2022-using</identifier>
<identifier type="doi">10.18653/v1/2022.computel-1.18</identifier>
<location>
<url>https://aclanthology.org/2022.computel-1.18</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>139</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Graph-Based Methods to Augment Online Dictionaries of Endangered Languages
%A Alnajjar, Khalid
%A Hämäläinen, Mika
%A Tapio Partanen, Niko
%A Rueter, Jack
%Y Moeller, Sarah
%Y Anastasopoulos, Antonios
%Y Arppe, Antti
%Y Chaudhary, Aditi
%Y Harrigan, Atticus
%Y Holden, Josh
%Y Lachler, Jordan
%Y Palmer, Alexis
%Y Rijhwani, Shruti
%Y Schwartz, Lane
%S Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F alnajjar-etal-2022-using
%X Many endangered Uralic languages have multilingual machine readable dictionaries saved in an XML format. However, the dictionaries cover translations very inconsistently between language pairs, for instance, the Livonian dictionary has some translations to Finnish, Latvian and Estonian, and the Komi-Zyrian dictionary has some translations to Finnish, English and Russian. We utilize graph-based approaches to augment such dictionaries by predicting new translations to existing and new languages based on different dictionaries for endangered languages and Wiktionaries. Our study focuses on the lexical resources for Komi-Zyrian (kpv), Erzya (myv) and Livonian (liv). We evaluate our approach by human judges fluent in the three endangered languages in question. Based on the evaluation, the method predicted good or acceptable translations 77% of the time. Furthermore, we train a neural prediction model to predict the quality of the automatically predicted translations with an 81% accuracy. The resulting extensions to the dictionaries are made available on the online dictionary platform used by the speakers of these languages.
%R 10.18653/v1/2022.computel-1.18
%U https://aclanthology.org/2022.computel-1.18
%U https://doi.org/10.18653/v1/2022.computel-1.18
%P 139-148
Markdown (Informal)
[Using Graph-Based Methods to Augment Online Dictionaries of Endangered Languages](https://aclanthology.org/2022.computel-1.18) (Alnajjar et al., ComputEL 2022)
ACL