A semantic grading model integrated local and global semantic relatedness for English text

This paper proposed a semantic grading model (SGM) for English text based on its content in different views. The SGM not only assesses the global semantic relatedness between ideal text and tested essay, local semantic relatedness between adjoining text segments, as well as the semantic relationship between vary text segments and the whole texts are also taken into account. Local and global semantic relatedness are combined to measure the overall quality of text contents on the basis of semantic. Our experiment shows that the SGM is competent in assessing the content of English text in terms of semantic grading.

[1]  Theo Tryfonas,et al.  Frontiers in Artificial Intelligence and Applications , 2009 .

[2]  Karen Spärck Jones.  A statistical interpretation of term specificity and its application in retrieval , 2021, J. Documentation.

[3]  Marian Petre,et al.  Seeing the Whole Picture: Evaluating Automated Assessment Systems , 2007 .

[4]  Stephen E. Robertson,et al.  Understanding inverse document frequency: on theoretical arguments for IDF , 2004, J. Documentation.

[5]  Karen Sparck Jones.  A statistical interpretation of term specificity and its application in retrieval , 1972 .

[6]  Gustaf Neumann,et al.  Factors Influencing Effectiveness in Automated Essay Scoring with LSA , 2005, AIED.

[7]  Peter W. Foltz,et al.  The intelligent essay assessor: Applications to educational technology , 1999 .

[8]  Jill Burstein,et al.  Automated Essay Scoring : A Cross-disciplinary Perspective , 2003 .

[9]  Ricardo Olmos,et al.  Latent Semantic Analysis Parameters for Essay Evaluation using Small-Scale Corpora* , 2010, J. Quant. Linguistics.

[10]  Susan T. Dumais,et al.  Latent semantic analysis , 2005, Scholarpedia.

[11]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[12]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[13]  Benoît Lemaire,et al.  A System to Assess the Semantic Content of Student Essays , 2001 .

[14]  Karen Spärck Jones.  IDF term weighting and IR research lessons , 2004, J. Documentation.

[15]  J. Quesada.  Creating Your Own LSA Spaces , 2007 .

[16]  Steve G. Romaniuk.  Using Intelligent Agents to Identify Missing and Exploited Children , 2000, IEEE Intell. Syst..

[17]  Guo Li Chen Yue.  Latent Semantic Indexing and Its Application , 2001 .

[18]  Gustaf Neumann,et al.  Parameters driving effectiveness of automated essay scoring with LSA , 2005 .