Fine-tuning XLM-RoBERTa-base with separate models per language-domain pair outperforms few-shot LLMs for multilingual dimensional aspect sentiment regression.
InProceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 19–30, San Diego, California
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
-
NCL-BU at SemEval-2026 Task 3: Fine-tuning XLM-RoBERTa for Multilingual Dimensional Sentiment Regression
Fine-tuning XLM-RoBERTa-base with separate models per language-domain pair outperforms few-shot LLMs for multilingual dimensional aspect sentiment regression.