@inproceedings{partanen-2024-using,
title = "Using Large Language Models to Transliterate Endangered {U}ralic Languages",
author = "Partanen, Niko",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
Pirinen, Flammie and
Macias, Melany and
Crespo Avila, Mario},
booktitle = "Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages",
month = nov,
year = "2024",
address = "Helsinki, Finland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwclul-1.10",
pages = "81--88",
abstract = "This study investigates whether the Large Language Models are able to transliterate and normalize endangered Uralic languages, specifically when they have been written in early 20th century Latin script based transcription systems. We test commercially available closed source systems where there is no reason to expect that the models would be particularly adjusted to this task or these languages. The output of the transliteration in all experiments is contemporary Cyrillic orthography. We conclude that some of the newer LLMs, especially Claude 3.5 Sonnet, are able to produce high quality transliterations even in the smaller languages in our test set, both in zero-shot scenarios and with a prompt that contains an example of the desired output. We assume that the good result is connected to the large presence of materials in these languages online, which the LLM has learned to represent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="partanen-2024-using">
<titleInfo>
<title>Using Large Language Models to Transliterate Endangered Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melany</namePart>
<namePart type="family">Macias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Crespo Avila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Helsinki, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study investigates whether the Large Language Models are able to transliterate and normalize endangered Uralic languages, specifically when they have been written in early 20th century Latin script based transcription systems. We test commercially available closed source systems where there is no reason to expect that the models would be particularly adjusted to this task or these languages. The output of the transliteration in all experiments is contemporary Cyrillic orthography. We conclude that some of the newer LLMs, especially Claude 3.5 Sonnet, are able to produce high quality transliterations even in the smaller languages in our test set, both in zero-shot scenarios and with a prompt that contains an example of the desired output. We assume that the good result is connected to the large presence of materials in these languages online, which the LLM has learned to represent.</abstract>
<identifier type="citekey">partanen-2024-using</identifier>
<location>
<url>https://aclanthology.org/2024.iwclul-1.10</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>81</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Large Language Models to Transliterate Endangered Uralic Languages
%A Partanen, Niko
%Y Hämäläinen, Mika
%Y Pirinen, Flammie
%Y Macias, Melany
%Y Crespo Avila, Mario
%S Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages
%D 2024
%8 November
%I Association for Computational Linguistics
%C Helsinki, Finland
%F partanen-2024-using
%X This study investigates whether the Large Language Models are able to transliterate and normalize endangered Uralic languages, specifically when they have been written in early 20th century Latin script based transcription systems. We test commercially available closed source systems where there is no reason to expect that the models would be particularly adjusted to this task or these languages. The output of the transliteration in all experiments is contemporary Cyrillic orthography. We conclude that some of the newer LLMs, especially Claude 3.5 Sonnet, are able to produce high quality transliterations even in the smaller languages in our test set, both in zero-shot scenarios and with a prompt that contains an example of the desired output. We assume that the good result is connected to the large presence of materials in these languages online, which the LLM has learned to represent.
%U https://aclanthology.org/2024.iwclul-1.10
%P 81-88
Markdown (Informal)
[Using Large Language Models to Transliterate Endangered Uralic Languages](https://aclanthology.org/2024.iwclul-1.10) (Partanen, IWCLUL 2024)
ACL