Papers with network design
Next Visit Diagnosis Prediction via Medical Code-Centric Multimodal Contrastive EHR Modelling with Hierarchical Regularisation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies have not addressed the heterogeneous and hierarchical properties inherent in EHR data. |
| Approach: | They propose a medical code-centric multimodal contrastive EHR learning framework with hierarchical regularisation that integrates multifaceted information encompassing medical codes, demographics, and clinical notes. |
| Outcome: | The proposed framework integrates multifaceted information encompassing medical codes, demographics, and clinical notes using a tailored network design and bimodal contrastive losses. |
Dynamic Routing Transformer Network for Multimodal Sarcasm Detection (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal sarcasm detection rely on fixed architectures to capture cross-modal incongruity. |
| Approach: | They propose a method that uses dynamic paths to activate different routing transformer modules with hierarchical co-attention adapting to cross-modal incongruity. |
| Outcome: | The proposed method is compared to state-of-the-art methods on a public dataset. |
Adapting RNN Sequence Prediction Model to Multi-label Set Prediction (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to multi-label classification are based on pre-specifying the label order, or relating the sequence probability to the set probability in ad hoc ways. |
| Approach: | They propose a new training objective that maximizes this set probability and a prediction objective that finds the most probable set on a test document. |
| Outcome: | The proposed model outperforms existing methods on a set of labels for multi-label classification . the proposed model is based on 'set probability' and 'prediction objective' |