US 12,443,793 B2
Device, method and program for natural language processing
Jun Suzuki, Musashino (JP); Sho Takase, Musashino (JP); Kentaro Inui, Miyagi (JP); Naoaki Okazaki, Miyagi (JP); and Shun Kiyono, Miyagi (JP)
Assigned to NTT, Inc., Tokyo (JP); and TOHOKU UNIVERSITY, Sendai (JP)
Filed by NTT, Inc., Tokyo (JP); and TOHOKU UNIVERSITY, Sendai (JP)
Filed on Sep. 14, 2023, as Appl. No. 18/368,223.
Application 18/368,223 is a continuation of application No. 16/975,312, granted, now 11,797,761, previously published as PCT/JP2018/023961, filed on Jun. 25, 2018.
Claims priority of application No. 2018-034781 (JP), filed on Feb. 28, 2018.
Prior Publication US 2024/0005093 A1, Jan. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/00 (2019.01); G06F 40/20 (2020.01); G06F 40/279 (2020.01); G06F 40/58 (2020.01)
CPC G06F 40/20 (2020.01) [G06F 40/279 (2020.01); G06F 40/58 (2020.01)] 9 Claims
OG exemplary drawing
 
4. A system comprising:
a hardware processor that, when reading and executing a trained neural network system:
receives from the trained neural network system, a predicted result of output text corresponding to input text and alignment information indicating which part of the input text is a basis of information for generation with respect to the predicted result;
with respect to each of learning data given beforehand consisting of pairs of the input text for learning and correct output text for learning; and
updates each parameter of the trained neural network system, in accordance with a value of a loss function calculated based on the predicted result of the output text for learning and the alignment information,
wherein the trained neural network system, into which first natural language text is input, outputs second natural language text and alignment information, the second natural language text corresponding to the first natural language text, and the alignment information indicating, with respect to the second natural language text, which part of the first natural language text is a basis of information for generation.