Joint information extraction method based on weak supervised learning

The invention relates to the technical field of information extraction, and further discloses a joint information extraction method based on weak supervised learning. The method comprises the following steps of S1, collecting information to form a training corpus, matching the training corpus with entity pairs in a knowledge base to obtain a training set, classifying the information in the training set, performing label labeling according to information containing features, and inputting the information subjected to multi-label labeling into a joint extraction model; s2, extracting in a training set according to the information feature labels needing to be extracted, and labeling all feature labels of the target after the target is obtained; and S3, putting the label information obtained in the step S2 into a joint extraction model for extraction to obtain an extraction result. The weak supervised learning-based joint information extraction method can solve the problem of time-consuming and labor-consuming da