Relation extraction method for automatic knowledge graph construction system

Abstract

The invention relates to a relation extraction method for an automatic knowledge graph construction system ; the method comprises the steps: coding and converting a text into word vectors, and preliminarily extracting text features; generating a syntactic dependency tree by using a syntactic dependency structure of the text, weighting each relation category to generate a weighted dependency adjacency matrix, and extracting syntactic dependency information in the text by using a graph convolutional neural network; synchronously, directly acting a multi-head attention mechanism on the encoded text to generate an attention matrix, and extracting information except syntactic dependency information of the text by using a graph convolutional neural network with the same structure; and finally, obtaining feature representations of the two entities and sentences, scoring all possible relation categories by using a feedforward neural network and a normalized exponential function, and selecting a relation with the highest score as a relation classification result. According to the method, information of different dimensions of the text can be fully acquired, and an excellent effect is achieved on a public data set for relation extraction.

Description

technical field [0001] The invention belongs to the technical field of natural language processing and artificial intelligence, and in particular relates to a relation extraction method for a knowledge map automatic construction system. Background technique [0002] Relation extraction is a key subtask in the field of natural language processing and an important part of information extraction tasks. Relation extraction aims to extract the relationship information between entities from unstructured text. By combining with the task of named entity recognition, it can generate the three-dimensional data required for building a knowledge graph system, such as <subject, predicate (relation), object> tuple. [0003] Traditional relational extraction methods mainly use linguistic knowledge to analyze texts, use statistical and rule-based methods, and manually design extraction rules or kernel functions for text matching and relational extraction. However, due to the complex...

AI Technical Summary

Problems solved by technology

The current main work is focused on how to prune the dependency tree more effectively and cut off information irrelevant to relation extraction to improve the performance of the model. However, rule-based pruning also has artificial noise, while soft pruning based on attention mechanism Branches destroy the original dependency structure and cannot make full use of the rich information contained in the dependency matrix.

Images