Transformers
Enhanced Seq2Seq Autoencoder via Contrastive Learning
Introduced by Zheng et al. in Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text SummarizationESACL, or Enhanced Seq2Seq Autoencoder via Contrastive Learning, is a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization. The model adopts a standard Transformer-based architecture with a multilayer bi-directional encoder and an autoregressive decoder. To enhance its denoising ability, self-supervised contrastive learning is incorporated along with various sentence-level document augmentation.
Source: Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Continual Learning | 1 | 20.00% |
| Abstractive Text Summarization | 1 | 20.00% |
| Denoising | 1 | 20.00% |
| Sentence | 1 | 20.00% |
| Text Summarization | 1 | 20.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
