Ancient poem proposition method and system

Abstract

The embodiment of the invention provides an ancient poem proposition method. The method comprises the following steps: extracting at least one keyword of each poem in a poem training set based on a knowledge graph, determining the keyword as a semantic feature of each poem, and modeling the semantic feature of each poem by using a neural network to obtain a poem model of which the input is the semantic feature of the poem and the output is other semantic features with similar semantics; carrying out knowledge modeling on the poem training set by utilizing the knowledge graph to obtain a structured model of poem information in the poem training set; and associating the poem model and the structured model based on the semantic features of each poem, inputting a preset question type into theassociated poem model and structured model, and outputting a question corresponding to the preset question type. The embodiment of the invention further provides an ancient poem proposition system. According to the embodiment of the invention, modeling is carried out by using the semantic features of the poems, the relation words of the poems can be distinguished, rich poem information can be obtained by structuring the information of the poems, and questions with higher quality can be generated.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to an ancient poetry proposition method and system. Background technique [0002] With the application of natural language processing technology in various fields, there have been many methods for making proposition systems in the fields of education and question answering. As one of the symbols of Chinese culture, ancient poetry has always been a difficulty in the direction of natural language processing because it involves difficult and complex tasks such as pronunciation, rhythm, abstract intentions, and allusions. Now some experts use neural network technology to understand the semantics of ancient poems and extract abstract features, and then derive products such as reading comprehension, propositions, and poem generation. Based on the shortcomings of the neural network itself, the above tasks can only achieve simple and basic functions. [0003] In the process of r...

AI Technical Summary

Problems solved by technology

[0008] In order to at least solve the problem of using the neural network model in the prior art, there will be a large number of wrong questions, it is impos

Images