US 12,260,186 B2
Method of generating text, method of training model, electronic device, and medium
Zhe Hu, Beijing (CN); Jiachen Liu, Beijing (CN); and Xinyan Xiao, Beijing (CN)
Assigned to BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD., Beijing (CN)
Filed by BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD., Beijing (CN)
Filed on Nov. 22, 2022, as Appl. No. 17/992,436.
Claims priority of application No. 202210097054.9 (CN), filed on Jan. 26, 2022.
Prior Publication US 2023/0084438 A1, Mar. 16, 2023
Int. Cl. G06F 40/56 (2020.01); G06F 40/30 (2020.01)
CPC G06F 40/56 (2020.01) [G06F 40/30 (2020.01)] 19 Claims
OG exemplary drawing
 
1. A method of generating a text, the method comprising:
determining a reference feature representation of a target semantic information;
determining, based on the reference feature representation and at least one predetermined logical character, at least one sentence latent representation respectively corresponding to the at least one predetermined logical character, wherein the determining the at least one sentence latent representation respectively corresponding to the at least one predetermined logical character comprises:
generating, for each predetermined logical character in the at least one predetermined logical character, an initial sentence latent representation corresponding to the predetermined logical character, by using the reference feature representation and the predetermined logical character, and
determining the at least one sentence latent representation based on the initial sentence latent representation; and
generating a target text content based on the at least one sentence latent representation.
 
7. A method of training a text generation model, the method comprising training the text generation model by using a training sample, so as to obtain a trained text generation model, wherein the training sample comprises a target sample semantic information and a sample text content, wherein the text generation model is configured to implement the method according to claim 1.
 
9. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to at least:
determine a reference feature representation of a target semantic information;
determine, based on the reference feature representation and at least one predetermined logical character, at least one sentence latent representation respectively corresponding to the at least one predetermined logical character, wherein determination of the at least one sentence latent representation respectively corresponding to the at least predetermined logical character comprises:
generation, for each predetermined logical character in the at least one predetermined logical character, an initial sentence latent representation corresponding to the predetermined logical character, by using the reference feature representation and the predetermined logical character, and
determination of the at least one sentence latent representation based on the initial sentence latent representation; and
generate a target text content based on the at least one sentence latent representation.
 
13. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to at least train a text generation model by using a training sample, so as to obtain a trained text generation model, wherein the training sample comprises a target sample semantic information and a sample text content and wherein the text generation model is configured to implement the determining and generating functions of claim 9.
 
14. A non-transitory computer-readable storage medium having computer instructions therein, the computer instructions configured to cause a computer system to at least:
determine a reference feature representation of a target semantic information;
determine, based on the reference feature representation and at least one predetermined logical character, at least one sentence latent representation respectively corresponding to the at least one predetermined logical character, wherein determination of the at least one sentence latent representation respectively corresponding to the at least predetermined logical character comprises:
generation, for each predetermined logical character in the at least one predetermined logical character, an initial sentence latent representation corresponding to the predetermined logical character, by using the reference feature representation and the predetermined logical character, and
determination of the at least one sentence latent representation based on the initial sentence latent representation; and
generate a target text content based on the at least one sentence latent representation.