US 12,112,275 B2
Learning device, learning method and learning program
Kosuke Nishida, Tokyo (JP); Kyosuke Nishida, Tokyo (JP); Hisako Asano, Tokyo (JP); and Junji Tomita, Tokyo (JP)
Assigned to NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
Appl. No. 17/293,434
Filed by NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
PCT Filed Nov. 8, 2019, PCT No. PCT/JP2019/043867
§ 371(c)(1), (2) Date May 12, 2021,
PCT Pub. No. WO2020/100739, PCT Pub. Date May 22, 2020.
Claims priority of application No. 2018-215088 (JP), filed on Nov. 15, 2018.
Prior Publication US 2021/0383257 A1, Dec. 9, 2021
Int. Cl. G06N 5/04 (2023.01); G06F 40/20 (2020.01); G06N 3/045 (2023.01)
CPC G06N 5/04 (2013.01) [G06F 40/20 (2020.01); G06N 3/045 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A learning device comprising a processor configured to execute operations comprising:
determining scores based on similarity degrees between an input sentence and pieces of external knowledge stored in an external knowledge database;
selecting at least a part of the pieces of external knowledge based on the scores as search results;
acquiring an output to the input sentence based on predetermined arithmetic processing using the input sentence and the selected at least a part of the pieces of external knowledge as inputs;
determining, based on a combination of the input sentence, the acquired output, the selected pieces of external knowledge, and a true output given to the input sentence in advance, a reward, wherein the reward is based on a first index and a second index, the first index indicates correctness of the acquired output relative to the true output, and the second index indicates a quality of the selected at least a part of the pieces of external knowledge; and
learning a first neural network by updating parameters of the first neural network using the reward.