This paper explores a general approach to paraphrase generation using a pre-trained seq2seq model fine-tuned using a back-translated anatomy and physiology textbook. Human ratings indicate that the paraphrase model generally preserved meaning and grammaticality/fluency: 70% of meaning ratings were above 75, and 40% of paraphrases were considered…

This paper presents WikiMorph, a tool that automatically breaks down words into morphemes, etymological compounds (morphemes from root languages), and generates contextual definitions for each component. It comes in two flavors: a dataset and a deep-learning-based model. The dataset was extracted from Wiktionary and contains over 450k entries. We…

The study developed a model of linguistic constructs to predict writing quality for college basic writers and analyzed how those constructs changed following instruction. Analysis used a corpus of argumentative essays from a quasi-experimental, instructional study with 252 students (MacArthur, Philippakos, & Ianetta, 2015) that found large…

"Mentoring through the Transitions: Voices on the Verge" highlights the individuals, programs, and institutions succeeding in assisting STEM students through critical junctures such as high school to college, community college to four-year institution, and four-year institution to graduate school and beyond. It features the authentic…

Educators globally are continually encouraged to use data to inform instructional improvement in schools, yet while there have been many recent innovations in data visualization and data science, educators are rarely included in dashboard co-design. On December 5 and 6, 2019, the Education Data Analytics Collaborative Workshop was held at Teachers…