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…

A neural model in the form of a servo-mechanism is developed to account for certain aspects of language and speech in the human nervous system. Emphasis is placed on encoding processes as well as on-going feedback during production. (SW)