Legal document named entity recognition method and device and computer equipment

Abstract

The invention relates to a legal document named entity identification method and apparatus, and a computer device. The method comprises the steps of obtaining a legal document to be identified; inputting the legal document to be identified into the deep neural network model for identification to obtain an identification result; wherein the deep neural network model is obtained by training a language model through a plurality of legal document data with labels, a bidirectional recurrent neural network and a conditional random place; wherein the language model is obtained by training a Google Bert model through a plurality of corpora. According to the invention, the deep neural network model is adopted to carry out entity identification; extracting a character vector from a Chinese charactersequence of the legal document to be identified by adopting a language model obtained by training a Google Bert model; and inputting the character vectors into a bidirectional recurrent neural network, inputting the output codes of the bidirectional recurrent neural network into a linear chain conditional random field, and obtaining a recognition result, so that the network for realizing named entity recognition is simple in structure, low in training cost and high in prediction capability.

Description

technical field [0001] The present invention relates to a named entity recognition method, more specifically to a legal document named entity recognition method, device and computer equipment. Background technique [0002] Named entity recognition is one of the basic tasks of natural language processing. Its purpose is to identify named entities in unstructured text and classify these entities, such as person names, place names, organization names, time and number types with special meanings , and user-defined entity designations and categories, etc. Accurate named entity recognition can effectively improve the downstream tasks of NLP (Natural Language Processing, NATURAL LANGUAGE PROCESSING), and is widely used in information extraction, question answering systems, syntactic analysis, information retrieval, and sentiment analysis. Legal document text named entity recognition is to identify judicial-related entity information in legal documents, including the name of the de...

AI Technical Summary

Problems solved by technology

As a result, the identification system is not only time-consuming and labor-intensive, but also has high requirements for the professional background knowledge of the modeler, and has poor flexibility

As a concise and flexible end-to-end learning method, the method based on deep neural network and CRF can take character representation vector as input and learn model parameters in combination with context information, and use sentence-level log likelihood to effectively combine The advantage of CRF in sequence labeling is that the label transfer score is added to the objective function, but the input data of the above method, that is, the representation vector of the word is weak in representation using the random or pre-trained word2vec method, and the training model depends on Disadvantages such as large-scale labeled data, and the difficulty of training as the network structure expands

[0005] Therefore, it is necessary to design a new method to solve the problems of complex network structure, high training cost and weak predictive ability of existing named entity recognition schemes

Images