US 12,462,094 B2
Length-controlled text generation using a text processing model
Yujia Xie, Redmond, WA (US); Lesly Sadiht Miculicich Werlen, Kirkland, WA (US); Song Wang, Bellevue, WA (US); Pengcheng He, Sammamish, WA (US); Yuantao Wang, Issaquah, WA (US); Wei Xiong, Bellevue, WA (US); and Yanling Xiong, Sammamish, WA (US)
Assigned to Microsoft Technology Licensing, LLC., Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Dec. 9, 2022, as Appl. No. 18/064,218.
Prior Publication US 2024/0193350 A1, Jun. 13, 2024
Int. Cl. G06F 40/166 (2020.01); G06F 40/117 (2020.01); G06F 40/284 (2020.01); G06F 40/47 (2020.01); G06N 20/00 (2019.01)
CPC G06F 40/166 (2020.01) [G06F 40/117 (2020.01); G06F 40/284 (2020.01); G06F 40/47 (2020.01); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A system comprising:
a processor; and
a memory comprising computer program code for execution by the processor, wherein the computer program code, when executed by the processor, causes the system to:
obtain input text data and associated output text data;
determine a sentence count of the output text data, wherein the sentence count indicates a number of sentences within the output text data;
label the output text data with a sentence count label and a sentence number label using the determined sentence count; and
iteratively train a text processing machine learning (ML) model over multiple training iterations based on training data that includes the input text data, the output text data, and the sentence count, wherein iteratively training the text processing ML model includes, during each of the multiple training iterations, training the text processing ML model to generate model output text data from the input text data based on the sentence count, determining loss data based on a difference between the model output text data and the output text data, and adjusting weight values of the text processing ML model using the determined loss data.