US 12,112,130 B2
Counterfactual text stylization
Sharmila Reddy Nangi, Hyderabad (IN); Niyati Himanshu Chhaya, Hyderabad (IN); Hyman Chung, San Ramon, CA (US); Harshit Nyati, Kota (IN); Nikhil Kaushik, Panchkula (IN); and Sopan Khosla, Pittsburgh, PA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Nov. 3, 2021, as Appl. No. 17/518,471.
Prior Publication US 2023/0137209 A1, May 4, 2023
Int. Cl. G06F 40/253 (2020.01); G06F 3/04847 (2022.01); G06F 40/151 (2020.01); G06F 40/166 (2020.01); G06F 40/30 (2020.01)
CPC G06F 40/253 (2020.01) [G06F 3/04847 (2013.01); G06F 40/151 (2020.01); G06F 40/166 (2020.01); G06F 40/30 (2020.01)] 20 Claims
OG exemplary drawing
 
11. A system comprising:
a memory component; and
a processing device coupled to the memory component, the processing device to perform operations comprising:
disentangling a style representation and a content representation for input text by encoding text elements of the input text into a latent vector space that indicates the content representation and the style representation, the content representation specifying a semantic meaning of the input text and the style representation specifying one or more style attributes expressed by the input text;
generating a plurality of variants of the style representation for the input text by:
identifying a plurality of strengths for applying a target style to the style representation of the input text by processing the style representation for the input text using a multi-layer perceptron classifier configured with an objective to generate versions of the style representation that minimize differences from the style representation and express a different magnitude of the target style; and
outputting the plurality of variants of the style representation in a target style embedding by applying each of the plurality of strengths of the target style to the style representation for the input text;
generating stylized text that includes a plurality of stylized versions of the input text, each of the plurality of stylized versions of the input text including different positions of punctuation relative to the text elements of the input text, and being generated by concatenating one of the plurality of variants of the style representation with the content representation; and
outputting a display of the plurality of stylized versions of the input text.