Automated essay scoring based on Small Dataset Retrieval Algorithm(SDRA)
Luo Haijia · 2015
Automated Essay Scoring( AES) has always been difficult in the field of language testing. The first step towards AES is scoring model generated by datasets that have already been scored artificially; however,researchers are confronted with the lack of datasets. From a mathematical point of view,in fact,we can use only a small dataset to build up a scoring model. It can be compared to that generated by large datasets. Thus,to improve researchers' efficiency and data efficiency,a small dataset retrieval algorithm( SDRA) is presented here. We also illustrate experiments with a traditional large dataset scoring model,on an automated scoring software platform based on Latent Semantic Analysis( LSA). Experimental results show that SDRA can use 25% of data to achieve the effect which is similar to that achieved by the traditional large dataset scoring model,which verifies that SDRA is practicable and effective.