Entity relationship extraction method for automatically constructing data set

• Main Authors: LI JUN, HUANG YUANWEN, HENG YUFENG, WEI CHAO, FANG DONGLI
• Format: Patent
• Language: Chinese; English
• Published: 12.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides an entity relationship extraction method for automatically constructing a data set. The entity relationship extraction method comprises the following steps: 1, collecting and preprocessing corpora; 2, defining a triple dictionary table, and constructing a synonym table; 3, generating a training data set and a test data set by using an LTP tool; 4, training a network model according to the training data set; 5, performing entity and relationship prediction on the test data set through the trained network model; 6, optimizing the prediction result to obtain a triple data set. By the adoption of the scheme, text content can be automatically analyzed, and the problem that a training and testing data set is difficult to generate is effectively solved; according to the scheme, through optimization and adjustment of the bert model, the problem that extraction of the entity relationship needs to depend on a large number of resource calculations in the past is solved, theentity relationship in t