Scoring Spoken Responses Based on Content Accuracy
Fei Huang, Lei Chen, Jana Z. Sukkarieh · 2012
Accuracy of content have not been fully utilized in the previous studies on automated speaking assessment. Compared to writing tests, responses in speaking tests are noisy (due to recognition errors), full of incomplete sentences, and short. To handle these challenges for doing content-scoring in speaking tests, we propose two new methods based on information extraction (IE) and machine learning. Compared to using an ordinary content-scoring method based on vector analysis, which is widely used for scoring written essays, our proposed methods provided content features with higher correlations to human holistic scores. 1