Transformer model architecture for readability

A system comprising:

• a data repository storing a written electronic communication comprising an input sentence;
• and
• a computer processor for executing:
• a sentence transformer model configured to:
• process the input sentence to output a suggested set of sentences,
• an evaluation process configured to:
• evaluate, using a readability metric rule, a plurality of sentences in the written electronic communication,
• detect, while evaluating the plurality of sentences, that the input sentence satisfies a readability metric threshold of the readability metric rule,
• trigger, responsive to the input sentence satisfying the readability metric threshold, the sentence transformer model to obtain the suggested set of sentences,
• evaluate the suggested set of sentences along a set of acceptability criteria, and
• determine that the set of acceptability criteria is satisfied, and
• a graphical user interface configured to:
• present, responsive to the set of acceptability criteria being satisfied, the suggested set of sentences, and
• modify the written electronic communication with the suggested set of sentences to obtain a modified written electronic communication.

A method comprising:

• detecting, in a written electronic communication, an input sentence satisfying a readability metric threshold;
• processing, by a sentence transformer model responsive to the input sentence satisfying the readability metric threshold, the input sentence to output a suggested set of sentences;
• evaluating the suggested set of sentences along a set of acceptability criteria, wherein evaluating the suggested set of sentences along the set of acceptability criteria comprises:
• transforming, by a vector embedding model, the suggested set of sentences to a suggested set vector embedding,
• transforming, by the vector embedding model, the input sentence to an input sentence vector embedding, and
• calculating a similarity metric between the suggested set vector embedding and the input sentence vector embedding,
• determining that the acceptability criteria is satisfied based at least in part on the similarity metric satisfying a similarity threshold;
• automatically updating, responsive to the acceptability criteria being satisfied, the written electronic communication with the suggested set of sentences to obtain a modified written electronic communication;
• and
• transmitting the modified written electronic communication.