NotesFAQContact Us
Collection
Advanced
Search Tips
Showing one result Save | Export
Peer reviewed Peer reviewed
PDF on ERIC Download full text
Olney, Andrew M. – Grantee Submission, 2021
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…
Descriptors: Translation, Language Processing, Error Analysis (Language), Grammar