Papers with learning capabilities
Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern Recognition (2024.findings-eacl)
Copied to clipboard
| Challenge: | Techniques, Tactics and Procedures (TTPs) mapping is a difficult task for CTI extraction . conventional learning approaches target the problem in the classical multiclass/label classification setting . |
| Approach: | They propose a neural matching architecture that incorporates a sampling-based learn-to-compare mechanism to facilitate the learning process. |
| Outcome: | The proposed model reduces the complexity of competing over large label space. |
Visual Elements Mining as Prompts for Instruction Learning for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | VEMP uses visual elements with text symbols embedded in the image to classify sentiment polarity towards a given opinion target. |
| Approach: | They propose a visual element mining as prompts method to fuse visual and text semantic information into instruction prompts for TMSC. |
| Outcome: | The proposed method achieves state-of-the-art performance on two benchmark datasets. |
Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Unsupervised cross-lingual transfer is a process of transferring knowledge between languages without explicit supervision. |
| Approach: | They propose a framework that combines lexical and syntactic knowledge to enhance learning . they use a code-switching technique to implicitly teach lexica and a syntaktic-based graph attention network to help encode syntakic structure. |
| Outcome: | The proposed framework outperforms baselines of zero-shot cross-lingual transfer with 1.0 3.7 points on text classification, named entity recognition, and semantic parsing tasks. |