pypi.org : edu-segmentation
To improve EDU segmentation performance using Segbot. As Segbot has an encoder-decoder model architecture, we can replace bidirectional GRU encoder with generative pretraining models such as BART and T5. Evaluate the new model using the RST dataset by using few-shot based settings (e.g. 100 examples) to train the model, instead of using the full dataset.
Registry
- Documentation
- JSON
purl: pkg:pypi/edu-segmentation
License:
Latest release: over 1 year ago
First release: almost 2 years ago
Downloads: 1,116 last month
Last synced: 21 days ago
No dependent packages found.