Abstract | ||
---|---|---|
The use of speech technology in children's reading assess- ment can help teachers to diagnose reading diculties and plan appropriate interventions for a large number of stu- dents. We present a Bayesian Network model of student reading comprehension that can be used to estimate auto- matic scores for a child's spoken answers to open-ended ques- tions about a text. Through the use of features derived from language models capturing dierent degrees of comprehen- sion, we found that on the TBALL dataset we could achieve 0.8 correlation with reference comprehension scores derived from teachers, exceeding the teachers' own correlation with this same reference. This student model also proved to per- form without bias due to a speaker's native language, which was not the case for a comparable baseline method, nor for the teachers themselves. |
Year | Venue | DocType |
---|---|---|
2008 | WOCCI | Conference |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joseph Tepperman | 1 | 73 | 8.59 |
Matteo Gerosa | 2 | 172 | 13.14 |
Shrikanth Narayanan | 3 | 66 | 11.98 |