Entity relationship joint extraction method based on reinforcement learning

Abstract

The present invention relates to the technical field of artificial intelligence, and more particularly, to an entity relationship joint extraction method based on reinforcement learning. Firstly, theunstructured text, segmented words, and training word vectors for entity relation extraction can be obtained, and are input in LSTM by taking words as a unit, because the same entity in a sentence mayappear in different forms in different locations, and we do not know where the entities really useful for relationship extraction, so we can use reinforcement learning method to select these entities; after the entity selection is completed, if there is a consecutive one, we need to merge it into one entity. Finally, after removing the redundancy, if two entities are picked out, the word vectorsof these two entities and the sentence vectors of the final output of LSTM are stitched together, and the relations are classified by a fully connected neural network, otherwise the sentence is considered to be noisy.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and more specifically, relates to a method for jointly extracting entity-relationships based on reinforcement learning. Background technique [0002] Entity and relationship extraction is an important link in the process of knowledge graph construction, which can lay a good foundation for the establishment of knowledge graph. Because there are a lot of unstructured or semi-structured texts in the Internet, and to use these text information, we need to extract knowledge, and there are still many challenges in the current knowledge extraction technology. [0003] Reinforcement learning is an important machine learning method, which has many applications in the fields of intelligent control of robots and analysis and prediction. From the current point of view, reinforcement learning has great application prospects in the field of natural language processing. The reasons are ...

AI Technical Summary

Problems solved by technology

[0006] The disadvantage of the existing technology is that the method of using reinforcement learning to screen the datasets used in remote supervision can only be used for relational extraction of noisy datasets, if the dataset itself is relatively clean, or if you don’t just want to do relational extraction , then the method is not very useful

[0007] This method uses a reinforcement learning model containing three states and four actions to combine entity extraction and relationship extraction, so that the results of entity extraction and relationship extraction interact with each other, but the model structure of this method is relatively complex

Images