The fundamental problem faced by automatic text understanding in Natural Language Processing (NLP) is to identify semantically related pieces of text and integrate them together to compute the meaning of the whole text. However, the principle of compositionality runs into trouble very quickly when real language is examined with its frequent…

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…