Bidirectional GRU relation extraction data processing method and system, terminal and medium

Abstract

The invention belongs to the technical field of relation extraction, and discloses a bidirectional GRU relation extraction data processing method and system, a terminal and a medium, and the method comprises the steps: carrying out the preprocessing of a reference data set SemEval-2010Task 8; performing word vectorization on the corpus through an EMLo pre-training model; performing preliminary denoising processing on the word vectors through a multi-head attention mechanism; coding the word vector by using a Bi-GRU network to obtain a hidden layer vector containing context information in the sentence; the hidden layer vector serves as input and is transmitted to a keyword attention layer, and the attention weight is calculated by combining output of the hidden layer with the entity pair relative position feature and the entity hiding similarity feature; and inputting the hidden layer vector processed by the attention mechanism into a classification layer to obtain a final relation extraction result. Experimental results show that the model provided by the invention achieves the most advanced performance without any other NLP tools.

Description

technical field [0001] The invention belongs to the technical field of relation extraction, and in particular relates to a bidirectional GRU relation extraction data processing method, system, terminal and medium. Background technique [0002] At present, relational extraction occupies an important position in the field of natural language processing. It is the core task and an indispensable link of natural language processing such as question answering systems, information extraction, and knowledge graphs. At the same time, relational extraction is also a research hotspot in recent years. The task of relation extraction is to predict the relation type and direction between two labeled entities in text. [0003] The relationship extraction method based on deep learning is mainly based on CNN and RNN network to obtain context information in sentences. Zeng et al. proposed a model using deep convolutional neural network to extract features in sentences. Zhang et al. proposed t...

AI Technical Summary

Problems solved by technology

But at the same time, in the task of relation classification, this model with attention mechanism does not make full use of the information related to the expression in the data set, and this information has a prompt effect on the task of entity classification. In addition, the shortest dependency path ( SDP), part-of-speech tags (pos), hypernyms, synonyms and other features are all language features generated by related NLP tools. error effects, and greatly increase the computational effort of the model

[0005] Through the above analysis, the problems and defects of the existing technology are: in the task of relation classification, the existing model with attention mechanism does not make full use of the information related to the expression in the data set; at the same time, the existing model uses other processing The tool will cause the model to be affected by the errors generated by the tool, greatly increase the computational workload of the model, and increase the calculation time of the model; and the traditional word vector model cannot accurately represent a large number of polysemy in sentences; In the network layer for extracting text information, the existing model uses too many LSTM network parameters, which increases the risk of model overfitting to a certain extent, and increases the amount of calculation of the model, resulting in longer calculation time

Images