Papers with auto encoding
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (P18-1)
Copied to clipboard
| Challenge: | Existing encoder-decoder dialog models cannot output interpretable actions as in traditional systems. |
| Approach: | They propose an unsupervised discrete sentence representation learning method that integrates with existing encoder-decoder dialog models for interpretable response generation. |
| Outcome: | The proposed model can be integrated with existing encoder-decoder dialog models and discover interpretable semantics via either auto encoding or context predicting. |
MedCycle: Unpaired Medical Report Generation via Cycle-Consistency (2024.findings-naacl)
Copied to clipboard
| Challenge: | Generating medical reports for X-ray images presents a significant challenge . previous studies have required a specific labeling schema for images and reports . |
| Approach: | They propose a cycle-consistent mapping function that transforms image embeddings into report embedds and auto-encoding for medical report generation. |
| Outcome: | The proposed approach outperforms state-of-the-art results in unpaired chest X-ray report generation, showing improvements in both language and clinical metrics. |