Method and device for optimizing file question-answering system based on collaborative adversarial training

• Main Authors: WANG LINGLI, CHEN PINGGANG, WU CUNFENG, LOU XINYUAN, ZHENG WANGXIAN
• Format: Patent
• Language: Chinese; English
• Published: 06.09.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention provides an archive question-answering system optimization method and device based on collaborative adversarial training, and relates to the technical field of computers, and the method comprises the steps: generating an equivalent archive question-answering system according to an archive data set and archive feature vectors obtained in advance; generating a G-type prejudice archive sample and an O-type prejudice archive sample for the equivalent archive question-answering system; constructing a plurality of G-O type prejudice archive sample pairs according to the similarity of the samples to obtain a plurality of prejudice archive sample pair sets for collaborative confrontation training; and carrying out collaborative confrontation training on the set by utilizing the prejudice file samples to eliminate the prejudice of the original file question-answering system so as to obtain a fair file question-answering system. The method solves the problems that an existing file question-answering syste