Naslov
Multi-task learning for cross-lingual sentiment analysis

Autori
Thakkar, Gaurish ; Mikelić Preradović, Nives ; Tadić, Marko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 2nd International Workshop on Cross-lingual Event-centric Open Analytics / Demidova, Elena ; Hakimov, Sherzod ; Winters, Jane ; Tadić, Marko - Ljubljana, 2021, 76-84

Skup
2nd International Workshop on Cross-lingual Event-centric Open Analytics (CLEOPATRA 2021)

Mjesto i datum
Ljubljana, Slovenija, 12.04.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
sentiment analysis ; cross-lingual ; transfer learning ; multi-task learning ; news sentiment ; under-resourced languages

Sažetak
This paper presents a cross-lingual sentiment analysis of news articles using zero-shot and few-shot learning. The study aims to classify the Croatian news articles with the positive, negative, and neu- tral sentiment using the Slovene dataset. The system is based on a trilin- gual BERT-based model trained in three languages: English, Slovene, Croatian. The paper analyses different setups of using datasets in two languages and proposes a simple multi-task model to perform sentiment classification. The evaluation is performed using the few-shot and zero- shot scenarios in single-task and multi-task experiments for Croatian and Slovene.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti, Filologija

POVEZANOST RADA