Paper: Automatic detection of plagiarized spoken responses

ACL ID W14-1803
Title Automatic detection of plagiarized spoken responses
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2014
Authors

This paper addresses the task of auto- matically detecting plagiarized responses in the context of a test of spoken En- glish proficiency for non-native speakers. A corpus of spoken responses containing plagiarized content was collected from a high-stakes assessment of English profi- ciency for non-native speakers, and sev- eral text-to-text similarity metrics were implemented to compare these responses to a set of materials that were identified as likely sources for the plagiarized con- tent. Finally, a classifier was trained using these similarity metrics to predict whether a given spoken response is plagiarized or not. The classifier was evaluated on a data set containing the responses with pla- giarized content and non-plagiarized con- trol responses and achieved accuracies of 92.0% us...