Methods › Natural Language Processing › Transformers › ESACL
Enhanced Seq2Seq Autoencoder via Contrastive Learning
ESACL
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ESACL, 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.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
EsaCL: Efficient Continual Learning of Sparse Models 11 Jan 2024 · 0 repositories · arXiv:2401.05667
-
Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization 26 Aug 2021 · 2 repositories · arXiv:2108.11992
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Abstractive Text Summarization | 1 |
| Continual Learning | 1 |
| Contrastive Learning | 1 |
| Decoder | 1 |
| Denoising | 1 |
| Sentence | 1 |
| Text Summarization | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections