Graph convolution network relation extraction method based on dependency analysis and keywords

Abstract

The invention provides a graph convolutional network relationship extraction method based on dependency analysis and keywords, which comprises the following steps of: firstly, performing sentence dependency analysis on a structured text to generate a dependency analysis graph, and trimming sentences through keywords; obtaining a word embedding vector and a position embedding vector of the sentenceby utilizing word2vec, and performing splicing to obtain a word vector sequence; performing a bidirectional GRU neural network on the word vector sequence to obtain an output vector matrix; processing the output vector matrix by adopting a graph convolution network to obtain dependency representation of sentences; combining the output vector matrix and the dependency representation of the sentence through a multi-head attention mechanism to obtain a representation vector of the sentence; and establishing a relationship and entity type prediction model by adopting a softmax function, and taking the representation vector of the sentence as the input of the prediction model, thereby performing training to obtain a relationship with the maximum prediction probability as an extraction result.

Description

technical field [0001] The invention relates to the field of text relation extraction, in particular to a relation extraction method based on dependency parsing and a keyword-based graph convolution network. Background technique [0002] The output of relation extraction is generally a triplet (entity 1, relation, entity 2), indicating that there is a specific category of semantic relationship between entity 1 and entity 2. For example, the sentence "The capital of China is Beijing" can extract the relation ( China, the capital, Beijing) this triplet. The most commonly used methods for relation extraction are supervised learning and deep learning, both of which have achieved good results. [0003] Among them, the deep learning method is based on the neural network method. Although it has quite good performance in terms of accuracy and regression rate, it is very dependent on supervised data sets (such as ACE-05 and SemEval-2010task 8), and these supervised data All rely on...

AI Technical Summary

Problems solved by technology

[0005] However, the traditional model of remote supervision relies heavily on the manual design of features by experts in specific knowledge fields, which is too time-consuming and laborious, or uses natural language processing (NLP) annotations such as part-of-speech tagging and syntactic parsing to provide classification features, while NLP tools such as Named Entity Recognition (NER ), dependency analysis, etc., often have large errors, and more feature engineering will bring more errors, causing error propagation and accumulation on the entire task pipeline, and ultimately affecting the accuracy of subsequent relationship extraction

Images