This study explores using transfer learning in machine learning for natural language processing (NLP) to create generic automated essay scoring (AES) models, providing instant online scoring for statewide writing assessments in K-12 education. The goal is to develop an instant online scorer that is generalizable to any prompt, addressing the…

Language comprehension is remarkable in that we adapt easily to different forms of language use, from adapting to speakers' dialects, meanings of new slang words, and fictional worlds described in novels. While there is growing evidence comprehenders adapt their expectations for text during reading, the nature of these adaptation mechanisms…

This dissertation investigated the effects of technological mediation on second language (L2) learning, focusing, as a case study, on gains in listening perception of the subtle but important feature of pitch placement in Japanese. Pitch accent can be difficult to perceive for non-native speakers whose first language (L1) does not rely on pitch or…

A single subject study with multiple baselines across participants was used to explore the effect of giving access to picture-to-text software for writing to young students, with moderate autism, and documented difficulties with written language. For this intervention study, three participants, who had strengths in visual processing and who were…