Applying Part-of-Seech Enhanced LSA to Automatic Essay Grading

  title={Applying Part-of-Seech Enhanced LSA to Automatic Essay Grading},
  author={Tuomo Kakkonen and Niko Myller and Erkki Sutinen},
Latent Semantic Analysis (LSA) is a widely used Information Retrieval method based on " bag-of-words " assumption. However, according to general conception, syntax plays a role in representing meaning of sentences. Thus, enhancing LSA with part-of-speech (POS) information to capture the context of word occurrences appears to be theoretically feasible extension. The approach is tested empirically on a automatic essay grading system using LSA for document similarity comparisons. A comparison on… CONTINUE READING

Similar Papers

Loading similar papers…