Sentiment Analysis Using Aligned Word Embeddings for Uralic Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A3ZLBZFLX" target="_blank" >RIV/00216208:11320/23:3ZLBZFLX - isvavai.cz</a>

Výsledek na webu

<a href="http://arxiv.org/abs/2305.15380" target="_blank" >http://arxiv.org/abs/2305.15380</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2305.15380" target="_blank" >10.48550/arXiv.2305.15380</a>

Jazyk výsledku

švédština

Název v původním jazyce

Sentiment Analysis Using Aligned Word Embeddings for Uralic Languages

Popis výsledku v původním jazyce

"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."

Název v anglickém jazyce

Sentiment Analysis Using Aligned Word Embeddings for Uralic Languages

Popis výsledku anglicky

"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."

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů