Methods › Natural Language Processing › Transformers › SongNet
SongNet
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SongNet is an auto-regressive Transformer-based language model for rigid format text detection. Sets of symbols are tailor-designed to improve the modeling performance especially on format, rhyme, and sentence integrity. The attention mechanism is improved to impel the model to capture some future information on the format. A pre-training and fine-tuning framework is designed to further improve the generation quality.
Papers archive 2025-07-28
1 shown of 1, 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.
-
SongNet: Rigid Formats Controlled Text Generation 17 Apr 2020 · 2 repositories · arXiv:2004.08022Syntology ran 3 of 8 samples · 5 unverified
Tasks archive 2025-07-28
3 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 |
|---|---|
| Language Modelling | 1 |
| Sentence | 1 |
| Text Generation | 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