Automatic subjective question marking neural network model with concept enhanced representation and unidirectional attention implication

Abstract

The invention discloses an automatic subjective question marking neural network model with concept enhanced representation and unidirectional attention implication. A concept series in questions is automatically identified by combining a bidirectional long-short term memory neural network BiLSTM and a conditional random field CRF of machine learning; through a multi-head attention mechanism, enhanced representation modeling of a concept word embedding vector sequence on a answer word embedding vector sequence is realized; answer context information is coded through the BiLSTM; through a one-way attention implication matching mode, semantic inclusion of student answers to reference answers is estimated, information is gathered on the basis of one-way implication matching vectors, and probability distribution prediction of student answer score intervals is carried out. The model comprises a concept extraction layer, an answer presentation layer, a concept enhancement presentation layer, a context presentation layer, a one-way implication attention layer, an aggregation layer and a prediction layer. The model has the advantages that extra semantic analysis and artificial rules are not needed; the matching precision of paper marking is improved; and the adaptability and practicability of a paper marking system are expanded.

Description

technical field [0001] The invention relates to the automatic marking of examination papers in the field of educational technology and computer application technology, in particular to a neural network model for automatic marking of subjective questions with enhanced representation of concepts and one-way implication of attention. This model uses the computer as a tool, takes randomly input student answers as the processing object, and realizes end-to-end automatic marking of subjective questions through neural networks, which can be widely used in computer automatic marking systems for subjective questions in various fields. Background technique [0002] The test questions in the test paper are generally divided into two categories: objective questions and subjective questions in terms of the form of answer composition. The characteristics of objective questions are: single-choice questions, multiple-choice questions, and judgment questions whose answers are indicated by op...

AI Technical Summary

Problems solved by technology

[0006] In order to improve the accuracy of marking, some automatic marking methods for subjective questions based on syntactic analysis and semantic analysis have appeared. However, due to the low accuracy of syntactic analysis and the inability of semantic analysis to deal with the timing of sentences, this greatly limits the application range and practicability of this type of system.

Images