@inproceedings{hamalainen-2024-dag,
title = "{DAG}: Dictionary-Augmented Generation for Disambiguation of Sentences in Endangered {U}ralic Languages using {C}hat{GPT}",
author = {H{\"a}m{\"a}l{\"a}inen, Mika},
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-1.4",
pages = "36--40",
abstract = "We showcase that ChatGPT can be used to disambiguate lemmas in two endangered languages ChatGPT is not proficient in, namely Erzya and Skolt Sami. We augment our prompt by providing dictionary translations of the candidate lemmas to a majority language - Finnish in our case. This dictionary augmented generation approach results in 50{\%} accuracy for Skolt Sami and 41{\%} accuracy for Erzya. On a closer inspection, many of the error types were of the kind even an untrained human annotator would make.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamalainen-2024-dag">
<titleInfo>
<title>DAG: Dictionary-Augmented Generation for Disambiguation of Sentences in Endangered Uralic Languages using ChatGPT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</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>We showcase that ChatGPT can be used to disambiguate lemmas in two endangered languages ChatGPT is not proficient in, namely Erzya and Skolt Sami. We augment our prompt by providing dictionary translations of the candidate lemmas to a majority language - Finnish in our case. This dictionary augmented generation approach results in 50% accuracy for Skolt Sami and 41% accuracy for Erzya. On a closer inspection, many of the error types were of the kind even an untrained human annotator would make.</abstract>
<identifier type="citekey">hamalainen-2024-dag</identifier>
<location>
<url>https://aclanthology.org/2024.iwclul-1.4</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>36</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DAG: Dictionary-Augmented Generation for Disambiguation of Sentences in Endangered Uralic Languages using ChatGPT
%A Hämäläinen, Mika
%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 hamalainen-2024-dag
%X We showcase that ChatGPT can be used to disambiguate lemmas in two endangered languages ChatGPT is not proficient in, namely Erzya and Skolt Sami. We augment our prompt by providing dictionary translations of the candidate lemmas to a majority language - Finnish in our case. This dictionary augmented generation approach results in 50% accuracy for Skolt Sami and 41% accuracy for Erzya. On a closer inspection, many of the error types were of the kind even an untrained human annotator would make.
%U https://aclanthology.org/2024.iwclul-1.4
%P 36-40
Markdown (Informal)
[DAG: Dictionary-Augmented Generation for Disambiguation of Sentences in Endangered Uralic Languages using ChatGPT](https://aclanthology.org/2024.iwclul-1.4) (Hämäläinen, IWCLUL 2024)
ACL