Automatic correction system and method for simple answers

A short-answer, automatic technology, applied in the fields of instruments, electrical digital data processing, computer parts, etc., can solve problems such as lack of accuracy, difficulty in obtaining knowledge base resources, and defects in similarity comparison methods, so as to improve accuracy, The effect of reducing resource consumption and improving the accuracy of word segmentation

CN110175585APending Publication Date: 2019-08-27BEIJING FORESTRY UNIVERSITY
5 Cites 9 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2019-08-27

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to an automatic correction system for simple answers, which is characterized by comprising a text analysis and labeling module, a similarity comparison module and a similarity scoring module, and a client comprises a user input answer text, a user labeling word pair and a display result. According to the method, deep semantic analysis can be realized without depending on a knowledge base, and the similarity of answer texts is obtained by using an optimized word comparison method.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to an automatic correction system and method for short-answer questions, which mainly relates to a correction system and method for classifying Chinese short-answer questions by analyzing the semantic similarity of short texts, and belongs to the field of natural language processing. Background technique

[0002] Natural language processing is the theory and method of studying effective communication between humans and computers using natural language. After years of development, it has some good applications in the fields of semantic analysis and sentiment analysis. However, in terms of the application of automatic correction of short-answer questions, systematic research on natural language processing is not enough.

[0003] The key to automatic correction of short answer questions is to realize the comparison of similarity of short texts. At present, there are four main types of short text comparison methods: methods based on...

Examples

Embodiment Construction

[0026] In order to better understand the present invention, some basic concepts are firstly explained.

[0027] Dependency tuple: It is composed of dependency dominant words, dependency subordinate words and dependency relations. For example: the dependency tuple corresponding to "equipment and raw material" is equipment, raw material, conj, where conj is a parallel connection relationship. The dependencies in this article are based on Universal Dependencies (UD).

[0028]Dependency structure tree: A tree structure formed by analyzing the dependency grammar of a sentence, reflecting the dependency relationship between words in the sentence. Words of child nodes (subordinate words) are dependent on words of parent nodes (dominant words), and the category of the arc indicates the dependency relationship between the two words.

[0029] Below in conjunction with example and accompanying drawing, the technique that correction system of the present invention adopts, the technique ...