Natural language relation extraction method based on multi-task learning mechanism

Abstract

The invention discloses a natural language relation extraction method based on a multi-task learning mechanism. The method comprises the following steps: introducing information implied by different tasks by utilizing a plurality of auxiliary tasks to improve a relation extraction effect; introducing knowledge distillation to enhance the effect of assisting a task to guide and train a multi-task model, introducing a teacher annealing algorithm for relation and extraction based on multi-task learning to enable the effect of the multi-task model to serve as a single-task model of a guide task inan ultra-far mode, and finally improving the accuracy of relation extraction is improved. The method comprises the following steps: firstly, training on different auxiliary tasks to obtain a multi-task model for guiding training; then, a model learned by an auxiliary task and a real label are used as supervision information to guide the learning of a multi-task model at the same time; finally, evaluation is carried out on a SemEval2010 task-8 data set, and the performance of the model is superior to that of a model independently using improved BERT for relation extraction and is also superiorto that of a mainstream model based on deep learning relation extraction.

Description

technical field [0001] The invention relates to a relation extraction technology in natural language processing, in particular to a natural language relation extraction method based on a multi-task learning mechanism. Background technique [0002] With the advent of the era of big data and artificial intelligence, various types of information on the Internet are growing at an explosive rate, and how to obtain information from massive amounts of data has become an urgent problem to be solved. Information extraction is an important branch of natural language understanding. Its main goal is to automatically extract the unstructured information embedded in the text and then convert it into structured data. The related technical research is gradually emerging. Relation extraction, as an important subtask of information extraction, its main goal is to extract an entity-relationship triple relation(e1,e2) for a specific entity pair given a piece of text. Relational extraction, as ...

AI Technical Summary

Problems solved by technology

The method based on the convolutional neural network and its variants can effectively and automatically extract features, but it cannot accurately characterize the time series problem; the method based on the recurrent neural network and its variants can automatically capture the sequence in time. dependencies, but cannot effectively deal with long-distance dependencies in sequences

In addition, these deep neural network-based methods often need to rely on additional high-level natural language processing tools to obtain lexical, syntactic, and semantic information, and these additional processing steps will accumulate errors.

These problems have hindered the further improvement of the relationship extraction task, so there is an urgent need to establish a more effective relationship extraction model

Images