Paper: Towards Automatic Scoring of a Test of Spoken Language with Heterogeneous Task Types

ACL ID W08-0912
Title Towards Automatic Scoring of a Test of Spoken Language with Heterogeneous Task Types
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2008
Authors

This paper describes a system aimed at auto- matically scoring two task types of high and medium-high linguistic entropy from a spoken English test with a total of six widely differing task types. We describe the speech recognizer used for this system and its acoustic model and lan- guage model adaptation; the speech features computed based on the recognition output; and finally the scoring models based on mul- tiple regression and classification trees. For both tasks, agreement measures between machine and human scores (correlation, kappa) are close to or reach inter-human agreements.