A dispute focus detection method and device based on deep learning hybrid model

Abstract

The invention relates to a dispute focus detection method and device based on a deep learning mixed model, belonging to the field of natural language processing. The method includes the following steps: ①Constructing a tree bank of disputed focus; ②Completing the data labeling and obtaining a data set; ③Obtaining a complete and trainable data set; ④Preprocessing the data set obtained in step S3 for Chinese data; ⑤Using BERT‑ The wwm model obtains the text word vector matrix; ⑥Use the LSTM network model to extract the global semantic features of the text; use various convolution kernels of the TextCNN model to extract the local semantic features of different granularities of the text; average the probability results of the two models, set The threshold is predicted, and the output probability exceeds the threshold of controversy. Aiming at the problem that a single model cannot capture and utilize multi-level semantic features at the same time, the present invention provides a mixed model method for predicting the focus of disputes, which greatly improves the prediction accuracy.

Description

technical field [0001] The invention belongs to the field of natural language processing, and relates to a dispute focus detection method and device based on a deep learning mixed model. Background technique [0002] With the vigorous development of cognitive intelligence such as natural language processing in the judicial field, text classification technology will provide scientific and technical support for solving the problems of intelligent processing and analysis involved in judicial business. Automatically detect the focus of disputes in the case defense process through intelligent text classification technology, and provide support for judges, prosecutors and other judicial personnel to quickly and accurately analyze the key information of the case. [0003] Text classification can be performed by manual annotation or automatic annotation. In an era of exponential information growth, manually processing and classifying large amounts of text data is time-consuming and ...

AI Technical Summary

Problems solved by technology

The disadvantage of this technology is that it completely relies on manual labeling data, a large number of human resources and professional domain knowledge; the second is that the end-to-end seq2seq text generation model encoder needs to fully understand the semantic information of the original text to achieve a better decoding effect. The results are not as expected and unstable; third, the end-to-end seq2seq text generation model requires a long training time and is prone to the problem of unregistered words

Images