Semantic Change Detection on SemEval Task 1 EN Sub-task 2 2020
0.731Spearman CorrelationLLaMa 2 7B
Evaluation results
| Method | Links | |
|---|---|---|
| LLaMa 2 7BBackbone=Llama-2-7b-hf, Fine-tuning=QLoRA, Epochs=1, Learning rate=2e-4, LoRA Rank=8, LoRA Alpha=16, Training dataset=ALaSCA2024.04 | 0.731 | |
| Card2024.04 | 0.547 | |
| BERTType=Monolingual BERT, Strategy=Masking2024.04 | 0.45 | |
| Arefyev and Zhikov2024.04 | 0.299 |