Question-answering method and system for entity relationship extraction based on transfer learning

Abstract

The invention relates to the technical field of natural language processing, in particular to a question-answering method for entity relationship extraction based on transfer learning. The acquisitionof a relationship classification result comprises the steps: obtaining and preprocessing a source domain text data set and a target domain text data set; inputting the preprocessed data into a skip-gram model for training to obtain word vectors of the source domain text data and the target domain text data, obtaining position vectors of the source domain text data and the target domain text data,and cascading the position vectors with the word vectors to obtain joint feature vectors of the source domain text data and the target domain text data; inputting the joint feature vector of the source domain text data into a BiLSTM network for pre-training to obtain network parameters in the pre-training process and context information and semantic features of the source domain text data; and inputting the joint feature vector of the target domain text data into a BiLSTM _ CNN fusion model for retraining to obtain a high-dimensional feature vector of the target domain text data, sending thehigh-dimensional feature vector into a classifier, and outputting the relationship classification result. Question-answering accuracy can be improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing in the field of information technology, in particular to a question answering method and system for entity relationship extraction based on transfer learning. Background technique [0002] With the continuous development and promotion of Internet technology, network data content and fragmented information are showing explosive growth. As an important branch of artificial intelligence technology, knowledge graph uses its powerful semantic processing ability and open interconnection ability to organize information and knowledge in an orderly and organic manner, build a large-scale semantic network, and provide knowledge acquisition and information processing in the Internet age. convenience. As a subtask of knowledge graph construction, relational extraction mines the semantic relationship information of sentences from fine-grained unstructured text information, forms st...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem that the above-mentioned existing technology cannot obtain ideal learning effects in the training model under the condition that the number of samples in the target field is small, resulting in inaccurate relationship extraction results, the present invention proposes a fusion network based on BiLSTM_CNN and transfer learning The relationship extraction method, the method first uses the source domain text data with a large amount of data and high similarity with the target domain text data for pre-training, and uses the transfer learning method to retrain the pre-trained parameters, through this weight The migration method helps the target domain to complete the task of relation extraction with few sample data, improving the efficiency and accuracy of relation extraction

Images