Content big data-oriented small sample relation extraction method and device

Abstract

The invention discloses a content big data-oriented small sample relation extraction method and device. The method comprises the following steps: firstly, performing vectorization processing on sentences by utilizing a pre-training language model and a character-level LSTM; secondly, extracting text structure features through a double-affine mechanism and a graph neural network; simultaneously using [CLS] word vectors representing semantic information in word-level LSTM and BERT to integrate context information into word vectors of the entity pair, and constructing entity pair features containing context information; and finally, extracting the similarity and difference of sentence features through a similarity-difference relation network to perform small sample relation extraction. According to the method and device, small sample learning is applied in a content big data scene, text features are fully extracted, differences among different types of entity relations are described, and the accuracy of relation extraction is improved.

Description

technical field [0001] The invention relates to a small-sample relationship extraction method and device for content-oriented big data, belonging to the technical field of the Internet and big data. Background technique [0002] With the continuous development of the Internet industry, the text data in the Internet continues to grow at an exponential rate. The text data in the Internet has the characteristics of heterogeneity, fragmentation and multi-source, and it contains rich knowledge and information at the same time. Using the entity relationship extraction method can extract structured information representation from unstructured text data. Structured information representation plays a fundamental role in the construction of applications such as knowledge graphs, search engines, and intelligent question answering systems. In addition, only by rationally and efficiently organizing and managing the extracted structured information can we fully mine and utilize the inter...

AI Technical Summary

Problems solved by technology

Entity relationship extraction methods usually need to be carried out on the basis of entity labeling, but entity labeling is often time-consuming, labor-intensive and costly, so it is of great practical significance to study entity relationship extraction technology in small sample scenarios

[0003] In recent years, small-sample relationship extraction based on neural network models has become the mainstream method, but the existing small-sample relationship extraction methods consider fewer dimensions when extracting sentence features, and it is difficult to efficiently extract multi-dimensional features of text

At the same time, when using sentence features for relation extraction, existing small-sample relation extraction methods often only focus on the similarity between sentence features, while ignoring the differences between different types of entity relations.

Images