A Sentence Structure Information Acquisition Method Oriented to Relational Extraction

Abstract

The invention discloses a relationship extraction-oriented sentence structure information acquisition method. The method includes the following steps: step 1, extracting a relationship mention sentence containing two entities and known entity semantic relationship categories from a data set; step 2, Use entity markers and delimiters to separate and mark the entities in the relationship mention sentence extracted in step 1; step 3, perform vector mapping on the text based on the pre-trained word vector lookup table or random word vector lookup table; step 4 1. Convolute the vector matrix representing the text through the neural network to extract the sentence structure features; step 5, implement the maximum pooling operation on the convolutional results, and further obtain abstract features; step 6, fully connected, Softmax layer predicts the classification results . By marking and separating the sentence entities before the convolutional neural network, we can better obtain the semantic information of each part of the content, obtain the entity-centered sentence structure features, and perform relationship extraction to achieve a better performance.

Description

technical field [0001] The invention relates to a processing method for inputting data into a neural network, in particular to a relation extraction-oriented sentence structure information acquisition method, which belongs to the technical field of natural language processing. Background technique [0002] With the rapid popularization of computers around the world and the rapid development of Internet technology, all kinds of data such as video, audio, pictures, and text have surged, and a large amount of information has appeared in front of users in digital form. In order to cope with the severe challenges brought by the information explosion, there is an urgent need for professional automated tools to extract truly valuable information from massive amounts of data, and information extraction has emerged as the times require. Information extraction technology is a widely used information processing technology in the field of natural language processing, and relation extrac...

AI Technical Summary

Problems solved by technology

Entity semantic relationship extraction is performed by entity tags in the sentence, so that the neural network can obtain the relative position information and semantic connection information between the vocabulary and the entity pair in the sentence other than the entity, so as to obtain the structural information of the sentence centered on the two entities. And to a certain extent, it avoids the feature sparsity problem caused by traditional machine learning methods, thereby improving the performance of relationship extraction, and effectively solving the problem of not being able to make good use of sentence structure information.

Images