Paper: A Human-Computer Collaboration Approach to Improve Accuracy of an Automated English Scoring System

ACL ID W10-1011
Title A Human-Computer Collaboration Approach to Improve Accuracy of an Automated English Scoring System
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2010
Authors

This paper explores an issue of redundant errors reported while automatically scoring English learners’ sentences. We use a human-computer collaboration approach to eliminate redundant er- rors. The first step is to automatically select can- didate redundant errors using PMI and RFC. Since those errors are detected with different IDs although they represent the same error, the can- didacy cannot be confirmed automatically. The errors are then handed over to human experts to determine the candidacy. The final candidates are provided to the system and trained with a de- cision tree. With those redundant errors eliminat- ed, the system accuracy has been improved.