Intended Use

The Language Suggestion Model serves as a powerful tool for communications compliance. Once a sentence has been flagged as potentially noncompliant, this model recommends an alternative sentence structure for consideration. Its aim is to provide a possible rewrite that presents a more compliant, fair, and balanced version helping users better adhere to relevant regulatory guidelines.

License

The use of this model is subject to the Saifr License Agreement available at https://saifr.ai/azure-custom-license Use of Saifr’s models is subject in all respects to the custom license agreement between Saifr and the end user.  Saifr models are not intended to replace the end user’s legal, compliance, business, or other functions, or to satisfy any legal or regulatory obligations.  Note that all compliance responsibilities remain solely those of the end user and that certain communications may require review and approval by properly licensed individuals. Saifr is not responsible for determining compliance with rules and will not be liable for actions taken or not taken based on model use. 

Sample Inputs and Outputs (REST)

Example Request

You can use cURL or any REST Client to send request. Just add your token and test.

    curl https://<url.com> -X POST -d '{ "sentence": string }' -H "Authorization: Bearer <TOKEN>" -H "Content-Type: application/json"

Sample Input

{ "sentence": string }

where-

• sentence: A noncompliant sentence (Required)

Sample Output

{
  "input_sentence": string,
  "output_sentences": string[]
}

where-

• input_sentence: The input noncompliant sentence.
• output_sentences: A numpy array of suggested compliant sentences for the given input sentence.

If the model is unable to suggest a compliant sentence, the output_sentences array will as follows -

{
  "input_sentence": "This is a test sentence.",
  "output_sentences": ["unable to rewrite"]
}