dev-python/edu-segmentation (pypi)

Search

Package Information

Description:
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.

Versions

Version EAPI Keywords Slot
0.0.115 8 ~amd64 ~x86 0

Metadata

Maintainers

Raw Metadata XML
<pkgmetadata>
	<maintainer type="person">
		<email>gentoo@houseofsuns.org</email>
		<name>Markus Walter</name>
	</maintainer>
</pkgmetadata>

Lint Warnings

Manifest

Type File Size Versions
Unmatched Entries
Type File Size
DIST edu_segmentation-0.0.115.tar.gz 317046 bytes
EBUILD edu-segmentation-0.0.115.ebuild 3293 bytes
MISC metadata.xml 250 bytes