Semi-automatic demand extraction method based on pre-training language fine tuning and dependency features

• Main Authors: LI TONG, WANG YUNDUO, ZHOU QIXIANG, DANG HONGBO
• Format: Patent
• Language: Chinese; English
• Published: 22.03.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a semi-automatic demand extraction method based on pre-training language fine tuning and dependency features. The semi-automatic demand extraction method comprises the following steps of preprocessing, entity extraction, entity fusion confirmation, intention extraction, intention fusion confirmation, subject relation post-processing and output modeling. According to the semi-automatic demand extraction method provided by the invention, the advantages of a pre-training language fine tuning model and dependency analysis characteristics are fused: on one hand, rules are designed for the field problem of software demand modeling, and the interpretability and reliability of the system are improved through field knowledge; and on the other hand, proper fine adjustment is performed by utilizing the generalization convenience of the pre-training language model, and additional large-scale data set labeling training cannot be paid for the accuracy premium. 本发明公开了基于预训练语言微调与依存特征的半自动需求抽取方法，包含以下步骤：预