Entity relationship identification method and device and computer readable storage medium
The invention provides an entity relationship identification method and device and a computer readable storage medium, and the entity relationship identification method comprises the steps: inputtinga to-be-identified text into a preset recurrent neural network model based on an artificial feature a...
Saved in:
Main Authors | , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
04.12.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention provides an entity relationship identification method and device and a computer readable storage medium, and the entity relationship identification method comprises the steps: inputtinga to-be-identified text into a preset recurrent neural network model based on an artificial feature and an attention mechanism, and carrying out the entity relationship identification, wherein the recurrent neural network model based on the artificial features and the attention mechanism is obtained by training based on a training sample text and sentence-level artificial features of the trainingsample text, and the artificial features comprise at least one of the following features: a first feature, a second feature and a third feature; wherein the length of the sentence, the semantic distance between entity pairs included in the sentence and the number of entities included in the sentence are determined; and outputting a recognition result of an entity relationship between preset entities in the to-be-recognized |
---|---|
Bibliography: | Application Number: CN201910401516 |