In recent years, with the promotion and application of artificial intelligence technology in all fields, English has also had a lot of attention and automatic grading areas, but not much in the text of the characterization of breakthrough, the traditional technology based on latent semantic analysis of the text said, more latent semantic analysis technology can extract thematic information, and information is ignored. The purpose of this paper is to better reflect the content of the text, evaluate the English level more accurately, and improve students' English level better. This paper proposes a text representation method based on word vector clustering and a text representation method based on vector space model. A TF-IDF algorithm based on word vector is proposed. It is verified that the quadratic weighted Kappa value of the prediction results of the multi-model fusion algorithm based on word vector is better than the first place in Kaggle international English composition scoring competition, which verifies the effectiveness of the algorithm.
CITATION STYLE
Saihanqiqige. (2020). Application research of English scoring based on TF-iDF clustering algorithm. In IOP Conference Series: Materials Science and Engineering (Vol. 750). Institute of Physics Publishing. https://doi.org/10.1088/1757-899X/750/1/012215
Mendeley helps you to discover research relevant for your work.