You can deploy this model and start earning money today!

marmolpen3/
sla-obligations-rights

Views

No views yet

marmolpen3/sla-obligations-rights

This is a SetFit model that can be used for SLA sentence obligation and right classification. The model has been trained using an efficient few-shot learning technique that involves:

Fitting a Sentence Transformer with contrastive learning.
Training a classification head with the features of the fitted sentence transformer.

This model has been trained with SLA sentences from real providers that offer software as a service. The outputs will be of numerical value, 0, 1 or 2, these being obligation, right, none respectively.

Usage

To use this model for inference, first install the SetFit library:

python -m pip install setfit

You can then run inference as follows:

python

from setfit import SetFitModel

# Download from Hub and run inference
model = SetFitModel.from_pretrained("marmolpen3/sla-obligations-rights")
# Run inference
preds = model(["NTTA's goal is to deliver SCD Content 100% of the time.", "You can request for a service credit by contacting Support."])
# Solution [0, 1] = ["Obligation", "Right"]

BibTeX entry and citation info

We are developing a system, it is in process, but you can visit it and contribute here

SetFit is the framework we use to train the model:

bibtex

@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}

The model used is paraphrase-mpnet-base-v2. If you need it you can cite their publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:

bibtex

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}