Paper: Evaluating Multiple Aspects Of Coherence In Student Essays

ACL ID N04-1024
Title Evaluating Multiple Aspects Of Coherence In Student Essays
Venue Human Language Technologies
Session Main Conference
Year 2004
Authors

CriterionSM Online Essay Evaluation Service includes a capability that labels sentences in student writing with essay-based discourse el- ements (e.g. , thesis statements). We describe a new system that enhances Criterion’s capa- bility, by evaluating multiple aspects of co- herence in essays. This system identifies fea- tures of sentences based on semantic similarity measures and discourse structure. A support vector machine uses these features to capture breakdowns in coherence due to relatedness to the essay question and relatedness between discourse elements. Intra-sentential quality is evaluated with rule-based heuristics. Results indicate that the system yields higher perfor- mance than a baseline on all three aspects.