System and method for automatically scoring college English compositions independent of manual pre-scoring

Abstract

The invention discloses a system and a method for automatically scoring college English compositions independent of manual pre-scoring. The system comprises a training composition characteristic word-composition matrix generating module, a training composition semantics space constructing module, an automatic scoring module of a composition to be scored, wherein a processing result, namely, a ''characteristic word-composition matrix'', of a ''construction characteristic word-composition matrix'' processing unit in the training composition characteristic word-composition matrix generating module is input into a ''construction training composition set semantics space'' processing unit in the training composition semantics space constructing module; and a processing result, namely, a ''full score composition set semantics space'', of a ''mapping full score composition set characteristic word frequency vector quantity to a training composition set semantics space'' processing unit in the training composition semantics space constructing module is input into a ''score calculating of the composition to be scored'' processing unit in the automatic scoring module of the composition to be scored. With the adoption of the system, workload of college English teachers in reading student English compositions is reduced greatly, and moreover, reliability and efficiency on scoring are high.

Description

technical field [0001] The invention relates to an automatic scoring technology and method for college English compositions in Chinese universities, in particular to an automatic scoring system and scoring method for college English compositions that do not rely on manual pre-scoring. Background technique [0002] The research on English composition automatic scoring technology originated from the PEG system developed by Ellis Page et al. of Duke University in the United States in 1966. The existing English composition automatic scoring system can be divided into three categories: the English composition automatic scoring system that focuses on language features, such as the PEG system; the English composition automatic scoring system that focuses on different content, such as the IEA system and the BETSY system; Composition automatic scoring system, such as e-rater system, IntelliMetric system, Liang Maocheng system, etc. Among them, the PEG system takes the quantifiable p...

AI Technical Summary

Problems solved by technology

Therefore, the reliability and validity of the scoring results will not be ideal if the existing foreign English composition automatic scoring technology is used to score Chinese college English composition

Moreover, the current research on automatic grading technology for English composition is mainly to solve the problem of automatic grading of English composition in large-scale English examinations. Usually, it is aimed at an English composition topic to be graded, using artificial pre-grading composition training for different scores of the topic. A scoring model was developed, and the obtained scoring model was used to score the composition to be graded. This method has good reliability and validity when scoring the composition to be graded with the same topic as the artificial pre-scored composition, but when grading the composition It is difficult to collect manually pre-graded essays with different scores

Because this method collects artificial pre-graded compositions of different scores for each topic when grading a composition to be graded, it is less feasible to promote in the actual English teaching in Chinese colleges and universities.

Images