Learn More
We show how the Barzilay and Lapata entity-based coherence algorithm (2008) can be applied to a new, noisy data domain – student essays. We demonstrate that by combining Barzilay and Lapata's entity-based features with novel features related to grammar errors and word usage, one can greatly improve the performance of automated coherence prediction for(More)
Educators are interested in essay evaluation systems that include feedback about writing features that can facilitate the essay revision process. For instance, if the thesis statement of a student's essay could be automatically identified, the student could then use this information to reflect on the thesis statement with regard to its quality, and its(More)
Current education standards in the U.S. require school students to read and understand complex texts from different subject areas (e.g., social studies). However, such texts usually contain figurative language, complex phrases and sentences, as well as unfamiliar discourse relations. This may present an obstacle to students whose native language is not(More)
At ETS, our researchers have extensive experience in natural language processing (NLP) — a field that applies principles of computational linguistics and computer science to the task of creating computer applications that analyze human language. NLP is the basis for applications that we are developing to address the increasing demand for evaluating(More)
  • 1