Entity relationship classification method of unstructured text based on WordNet and IDF

Abstract

The invention discloses an entity relationship classification method of an unstructured text based on WordNet and IDF. The method comprises the following specific steps of (1) obtaining a text training set and performing preprocessing to obtain sentence matrix representation; (2) expanding external semantic information of sentences by utilizing WordNet; (3) expanding internal semantic informationof the sentences by utilizing IDF; (4) calculating position information of words in the sentences, and updating matrix representation of the sentences; and (5) inputting a sentence matrix in the step(4) into a segmented convolutional neural network to obtain feature vectors of the sentences; (6) inputting the feature vectors into a classifier, and calculating a loss function; (7) if the accuracyof the current round of training is improved by more than 0.1% compared with the accuracy of the previous round or reaches an upper limit of iteration, finishing the training of the classification method; otherwise, updating hyper-parameters in the step (5), and continuing the training process. According to the method, semantic features of entities and relations can be accurately expressed, so that the problem of overlarge noise of training set data is relieved, and the classification accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of text mining and deep learning, and is an entity relationship classification method based on WordNet and IDF unstructured text under remote supervised learning, which can be applied to building knowledge graphs, developing question answering systems, and information retrieval systems, etc. specific areas. Background technique [0002] Entity relationship extraction is one of the most important sub-topics in the field of information extraction. It is based on entity recognition to extract the semantic relationship between predefined entities from unstructured text. According to the degree of dependence on labeled data, entity relationship extraction methods can be divided into supervised relationship extraction, semi-supervised relationship extraction, unsupervised relationship extraction and distant supervision relationship extraction. [0003] Supervised relation extraction treats the relation extraction...

AI Technical Summary

Problems solved by technology

[0005] In summary, the current relationship extraction method under remote supervision mainly solves the problem that the relationship between a large amount of data is incorrectly labeled due to the introduction of strong assumptions in the process of automatically generating annotated training sets under remote supervision, which makes the training data a lot of noise.

Images