Introduces RoIt-XMASA dataset for Romanian and Italian multi-domain sentiment analysis and an adversarial training framework that raises XLM-R F1 to 66.23%.
(a) If your work uses existing assets, did you cite the cre- ators? Yes, we cite the original XMASA dataset cre- ators and the developers of models like XLM-R and Llama-3.1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian
Introduces RoIt-XMASA dataset for Romanian and Italian multi-domain sentiment analysis and an adversarial training framework that raises XLM-R F1 to 66.23%.