Deep learning-based department semantic information extraction method and device

Abstract

The invention relates to the technical field of language information processing, in particular to a deep learning-based department semantic information extraction method and device, and the method comprises the steps: carrying out the preprocessing of obtained user question data, and obtaining the preprocessing data; inputting the preprocessed data into a pre-trained BERT word coding model to obtain word vector data; inputting the word vector data into a pre-trained position attention mechanism BiLSTM model to obtain a data labeling result; and based on the data annotation result, extracting department semantic information in the user question data. According to the invention, the accuracy of department information extraction can be improved.

Description

technical field [0001] The present invention relates to the technical field of language information processing, in particular to a method and device for extracting departmental semantic information based on deep learning. Background technique [0002] Semantic information extraction of departments is to identify entities related to departments from telecom user questions, such as unit name, number, department name, number and other entities. Semantic information extraction is the basis of natural language processing tasks such as question answering systems and machine translation. The current research methods mainly include dictionary-based, machine learning-based and deep learning-based methods. [0003] Among them, the dictionary-based method constructs a large number of dictionaries and matches the text to be extracted to extract the departmental information in the text. The dictionary mainly includes information such as units and departments, and the quality of the dict...

AI Technical Summary

Problems solved by technology

[0005] At present, deep learning is still in its infancy in text information extraction. In some cases, existing neural network methods still have the following problems in solving departmental semantic information extraction: it is difficult to construct a large number of departmental information sample sets, and there are special nouns. The problem of inaccurate boundary recognition

Images