Downloads · 30 days
162
0% of all-time downloads
rubert-base-cased-conversational-paraphrase-v1
s-nlp/rubert-base-cased-conversational-paraphrase-v1
rubert-base-cased-conversational-paraphrase-v1 is a text classification model from s-nlp. Use it when you need a label for a piece of text. It is set up for transformers.
This is a ruBERT-conversational model trained on the mixture of 3 paraphrase detection datasets: - ruparaphraser (with classes -1 and 0 merged) - RuPAWS - A dataset containing crowdsourced evaluation of content preser…
All-time downloads
37.8K
Public
Parameters
178M
1.4 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin711 MB · 50%
Parameter types
How the weights are stored.
F32178M · 100%
Try a prompt
Datasets
Model card
From the Hugging Face model README
This is a ruBERT-conversational model trained on the mixture of 3 paraphrase detection datasets:
- ru_paraphraser (with classes -1 and 0 merged)
- RuPAWS
- A dataset containing crowdsourced evaluation of content preservation in Russian text detoxification by Dementieva et al, 2022.
The model can be used to assess semantic similarity of Russian sentences.
Training notebook: task_oriented_TST/similarity/cross_encoders/russian/train_russian_paraphrase_detector__fixed.ipynb (in a private repo).
Training parameters:
- optimizer: Adam
lr=1e-5batch_size=32epochs=3
ROC AUC on the development data:
source score
detox 0.821665
paraphraser 0.848287
rupaws_qqp 0.761481
rupaws_wiki 0.844093
Pleas see also the documentation of SkolkovoInstitute/ruRoberta-large-paraphrase-v1 that performs better on this task.
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Languages
- ru
- Created
- Jul 3, 2022
- Updated
- Mar 20, 2023