US 12,118,295 B2
Text simplification with minimal hallucination
Vinay Aggarwal, New Delhi (IN); Aparna Garimella, Telangana (IN); Ananya Ganesh, Chennai (IN); Niyati Himanshu Chhaya, Telangana (IN); and Nandakishore Kambhatla, Bangalore (IN)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Oct. 11, 2022, as Appl. No. 18/045,551.
Prior Publication US 2024/0119220 A1, Apr. 11, 2024
Int. Cl. G06F 17/00 (2019.01); G06F 40/166 (2020.01); G06F 40/289 (2020.01); G06F 40/30 (2020.01); G06N 3/082 (2023.01)
CPC G06F 40/166 (2020.01) [G06F 40/289 (2020.01); G06F 40/30 (2020.01); G06N 3/082 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for language processing, comprising:
identifying a simplified text that includes original information from a complex text and additional information that is not in the complex text;
computing an entailment score for each sentence of the simplified text using a neural network, wherein the entailment score indicates whether the sentence of the simplified text includes information from a sentence of the complex text corresponding to the sentence of the simplified text;
generating a modified text based on the entailment score, the simplified text, and the complex text, wherein the modified text includes the original information and excludes the additional information;
computing a first similarity score based on the complex text and the simplified text;
computing a second similarity score based on the complex text and the modified text;
comparing the first similarity score to the second similarity score; and
providing the modified text based on the comparison.