This article addresses Second Language (L2) writing development through an investigation of new grammatical and structural complexity metrics. We explore the paradigmatic production in learner English by linking language functions to specific grammatical paradigms. Using the EFCAMDAT as a gold standard and a corpus of French learners as an external test set, we employ a supervised learning framework to operationalise and evaluate seven microsystems. We show that learner levels are associated with the seven microsystems (MS). Using ordinal regression modelling for evaluation, the results show that all MS are significant but yield a low impact if taken individually. However, their influence is shown to be impactful if taken as a group. These microsystems and their measurement method suggest that it is possible to use them as part of broader-purpose CALL systems focused on proficiency assessment.

No, AI probably won't be put to use making sure you spell "adjudicate" correctly, or don't confuse they're and there. But it could turn into the sort of highly-integrated, barely-noticed, and pretty-much-essential technology that spellcheck has become. As legal tech enthusiasts gathered in "Washington, D.C.-adjacent" National Harbor Maryland this week, Microsystems CEO Stacy Kacek acknowledged that AI's uses in "real-world applications" are "still pretty limited," Legaltech News' Ian Lopez reports. But the technology could find itself highly integrated into your practice sooner or later, in subtle ways -- soon becoming as ubiquitous as spellcheck has become. David Cook, Microsystems' VP of product development, asked attorneys to imagine what would happen if they got rid of spellcheck throughout their practice.