Papers by Minna Peng
TicTac: Time-aware Supervised Fine-tuning for Automatic Text Dating (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models that ignore the temporal relatedness of documents are time-agnostic and therefore fail to perform in automatic text dating. |
| Approach: | They propose a supervised fine-tuning model for automatic text dating that captures temporal semantic information and uses a contrastive learning-based approach to model two types of temporal relations of diachronic documents. |
| Outcome: | The proposed model outperforms state-of-the-art models on two diachronic corpora and captures temporal semantic information. |