Papers › UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT...

UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis

1 Jun 2023arXiv:2306.01093archive 2025-07-28

Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu

This paper describes our system designed for SemEval-2023 Task 12: Sentiment analysis for African languages. The challenge faced by this task is the scarcity of labeled data and linguistic resources in low-resource settings. To alleviate these, we propose a generalized multilingual system SACL-XLMR for sentiment analysis on low-resource languages. Specifically, we design a lexicon-based multilingual BERT to facilitate language adaptation and sentiment-aware representation learning. Besides, we apply a supervised adversarial contrastive learning technique to learn sentiment-spread structured representations and enhance model generalization. Our system achieved competitive results, largely outperforming baselines on both multilingual and zero-shot sentiment classification subtasks. Notably, the system obtained the 1st rank on the zero-shot classification subtask in the official ranking. Extensive experiments demonstrate the effectiveness of our system.

Paper PDF Code

Code

zerohd4869/sacl mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive Learning Representation Learning Sentiment Analysis Sentiment Classification Zero-Shot Learning Zero-shot Sentiment Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Zero-shot Sentiment Classification	AfriSenti	SACL-XLMR	weighted-F1 score	0.589	#1 of 5	Archive leaderboard	report
Zero-shot Sentiment Classification	AfriSenti	AfroXLMR	weighted-F1 score	0.561	#2 of 5	Archive leaderboard	report
Zero-shot Sentiment Classification	AfriSenti	AfriBERTa	weighted-F1 score	0.439	#3 of 5	Archive leaderboard	report
Zero-shot Sentiment Classification	AfriSenti	XLM-R	weighted-F1 score	0.399	#4 of 5	Archive leaderboard	report
Zero-shot Sentiment Classification	AfriSenti	Random	weighted-F1 score	0.34	#5 of 5	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Contrastive Learning Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections