@inproceedings{alnajjar-etal-2023-sentiment,
title = "Sentiment Analysis Using Aligned Word Embeddings for {U}ralic Languages",
author = {Alnajjar, Khalid and
H{\"a}m{\"a}l{\"a}inen, Mika and
Rueter, Jack},
editor = "Ilinykh, Nikolai and
Morger, Felix and
Dann{\'e}lls, Dana and
Dobnik, Simon and
Megyesi, Be{\'a}ta and
Nivre, Joakim",
booktitle = "Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)",
month = may,
year = "2023",
address = "T{\'o}rshavn, the Faroe Islands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.resourceful-1.3",
pages = "19--24",
abstract = "In this paper, we present an approach for translating word embeddings from a majority language into 4 minority languages: Erzya, Moksha, Udmurt and Komi-Zyrian. Furthermore, we align these word embeddings and present a novel neural network model that is trained on English data to conduct sentiment analysis and then applied on endangered language data through the aligned word embeddings. To test our model, we annotated a small sentiment analysis corpus for the 4 endangered languages and Finnish. Our method reached at least 56{\%} accuracy for each endangered language. The models and the sentiment corpus will be released together with this paper. Our research shows that state-of-the-art neural models can be used with endangered languages with the only requirement being a dictionary between the endangered language and a majority language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alnajjar-etal-2023-sentiment">
<titleInfo>
<title>Sentiment Analysis Using Aligned Word Embeddings for Uralic 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">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tórshavn, the Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present an approach for translating word embeddings from a majority language into 4 minority languages: Erzya, Moksha, Udmurt and Komi-Zyrian. Furthermore, we align these word embeddings and present a novel neural network model that is trained on English data to conduct sentiment analysis and then applied on endangered language data through the aligned word embeddings. To test our model, we annotated a small sentiment analysis corpus for the 4 endangered languages and Finnish. Our method reached at least 56% accuracy for each endangered language. The models and the sentiment corpus will be released together with this paper. Our research shows that state-of-the-art neural models can be used with endangered languages with the only requirement being a dictionary between the endangered language and a majority language.</abstract>
<identifier type="citekey">alnajjar-etal-2023-sentiment</identifier>
<location>
<url>https://aclanthology.org/2023.resourceful-1.3</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>19</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Analysis Using Aligned Word Embeddings for Uralic Languages
%A Alnajjar, Khalid
%A Hämäläinen, Mika
%A Rueter, Jack
%Y Ilinykh, Nikolai
%Y Morger, Felix
%Y Dannélls, Dana
%Y Dobnik, Simon
%Y Megyesi, Beáta
%Y Nivre, Joakim
%S Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Tórshavn, the Faroe Islands
%F alnajjar-etal-2023-sentiment
%X In this paper, we present an approach for translating word embeddings from a majority language into 4 minority languages: Erzya, Moksha, Udmurt and Komi-Zyrian. Furthermore, we align these word embeddings and present a novel neural network model that is trained on English data to conduct sentiment analysis and then applied on endangered language data through the aligned word embeddings. To test our model, we annotated a small sentiment analysis corpus for the 4 endangered languages and Finnish. Our method reached at least 56% accuracy for each endangered language. The models and the sentiment corpus will be released together with this paper. Our research shows that state-of-the-art neural models can be used with endangered languages with the only requirement being a dictionary between the endangered language and a majority language.
%U https://aclanthology.org/2023.resourceful-1.3
%P 19-24
Markdown (Informal)
[Sentiment Analysis Using Aligned Word Embeddings for Uralic Languages](https://aclanthology.org/2023.resourceful-1.3) (Alnajjar et al., RESOURCEFUL 2023)
ACL
- Khalid Alnajjar, Mika Hämäläinen, and Jack Rueter. 2023. Sentiment Analysis Using Aligned Word Embeddings for Uralic Languages. In Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023), pages 19–24, Tórshavn, the Faroe Islands. Association for Computational Linguistics.