We introduce a short answer scoring engine made up of an ensemble of deep neural networks and a Latent Semantic Analysis-based model to score short constructed responses for a large suite of questions from a national assessment program. We evaluate the performance of the engine and show that the engine achieves above-human-level performance on a…

Intersectionality highlights that different aspects of individuals' identities are not independent of each other. Instead, they interact to create unique identities and experiences, which cannot be understood by analysing each identity dimension separately or in isolation from their social and historical contexts. Intersectional approaches in this…

The 2014-15 school year was the first in which the Smarter Balanced assessments (referred to here as the SBAC) were administered statewide. While educators and policymakers agree that multiple measures over multiple years are the best way to gauge student, school, and district performance, the first-year SBAC results provide an important baseline…

Many students graduate from high school unprepared for the rigorous reading required in entry-level college and career work. This brief builds on a recent report (Wilkins et al. 2010) that used the Lexile measure (a method for measuring the reading difficulty of prose text and the reading capability of individuals) to estimate the proportion of…