depth-indexed linearized dependency tree
Fine-grained Controllable Text Generation through In-context Learning with Feedback
Thillainathan, Sarubi, Koller, Alexander
We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth. In contrast to earlier work, our method uses in-context learning rather than finetuning, making it applicable in use cases where data is sparse. We show that our model performs accurate rewrites and matches the state of the art on rewriting sentences to a specified school grade level.
2406.11338
Country:
- South America > Argentina > Pampas > Buenos Aires F.D. > Buenos Aires (0.06)
- Atlantic Ocean (0.06)
- Europe > Lithuania (0.04)
- (7 more...)
Technology: