Method for analyzing sparse semantic relationship by combining BiLSTM-CRF algorithm and R-BERT algorithm

Abstract

The invention provides a method for analyzing a sparse semantic relationship by combining a BiLSTM-CRF algorithm and an R-BERT algorithm, which comprises the following steps: acquiring text data of emerging industries through a web crawler, and performing semi-supervised annotation on the text data; preprocessing the labeled text data, and constructing a training data set and a verification data set; training a BiLSTM-CRF algorithm model and an R-BERT algorithm model according to the training data set and the verification data set; extracting entities contained in the text data to be predictedthrough the trained BiLSTM-CRF algorithm model; predicting the relationship between the text data to be predicted and the entities through the trained RBERT algorithm model, and establishing relationship connection between the related entities; and extracting the triad pair of the semantic relationship of the text data to be tested according to the established relationship connection, and completing semantic analysis of the text data to be tested. The invention provides a high-precision semantic relation extraction method for information extraction of an unstructured text, a BiLSTM-CRF algorithm model is used for extracting required entities in the text, and the relation between the text and the extracted entities is predicted through an R-BERT model.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a semantic relationship analysis method based on deep learning and pre-training models and an efficient semi-supervised semantic entity relationship labeling construction method, in particular to a combination of BiLSTM-CRF algorithm A method for parsing sparse semantic relations with the R-BERT algorithm. Background technique [0002] With the rapid development of the Internet, the analysis and processing of massive Internet data has become a crucial task in various industries. Massive text data in the Internet, especially unstructured text data, contains a lot of important information, but also contains a lot of noise and Irrelevant information, the distribution of effective entities is relatively sparse, how to extract data information in unstructured text with high precision has become the top priority in industry analysis. [0003] In addition, manual text data re...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of the Internet, the analysis and processing of massive Internet data has become a crucial task in various industries. Massive text data in the Internet, especially unstructured text data, contains a lot of important information, but also contains a lot of noise and Irrelevant information, the distribution of effective entities is relatively sparse, how to extract data information in unstructured text with high precision has become the top priority in industry analysis

[0003] In addition, manual text data relationship extraction relies on a large number of human resources to mine the relationship between entities in massive data. Traditional machine learning methods are difficult to achieve high precision in semantic analysis, and at the same time, insufficient annotation data and high annotation Cost has also become a factor affecting the accuracy of semantic entity relationship extraction

[0004] The distribution of market data in unstructured articles on the Internet is relatively sparse, and irrelevant information brings a lot of noise to the judgment of the relationship between market data values ​​and their designated products and time

Images