Large Language Models (LLM) -- powerful algorithms that can generate and transform text -- are set to disrupt language learning education and text-based assessments as they allow for automation of text that can meet certain outcomes of many traditional assessments such as essays. While there is no way to definitively identify text created by this…

Citizens need the capability to conduct their own inquiry projects so that they can make sense of claims about new energy policies, health remedies, or financial opportunities. To develop the lifelong capability to grapple with these dilemmas, we report on ways to design precollege units that engage students in realistic, personally relevant…

E-rater[R] is an automated essay scoring system that uses natural language processing techniques to extract features from essays and to model statistically human holistic ratings. Educational Testing Service has investigated the use of e-rater, in conjunction with human ratings, to score one of the two writing tasks on the TOEFL-iBT[R] writing…

We present a new feedback strategy implemented in a natural language generation-based e-learning system for German as a second language (L2). Although the system recognizes a large proportion of the grammar errors in learner-produced written sentences, its automatically generated feedback only addresses errors against rules that are relevant at…

We built an NLP system implementing a "virtual writing conference" for elementary-school children, with German as the target language. Currently, state-of-the-art computer support for writing tasks is restricted to multiple-choice questions or quizzes because automatic parsing of the often ambiguous and fragmentary texts produced by pupils…

Examines marginal and end comments written on the first drafts of essays of advanced university students of English as a Second Language in terms of their pragmatic goals and linguistic features. Findings indicate the importance of helping students process feedback successfully and providing text-specific feedback. (65 references) (Author/CK)