Papers by Gustavo Zomer
Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on tools for improving writing focuses mostly on Grammatical Error Corrrection (GEC) but it does not adequately address fluency and complex linguistic issues. |
| Approach: | They propose a method for training a writing improvement model adapted to the writer’s first language (L1) without using annotated training data and use parallel corpora of reference translation aligned with machine translation. |
| Outcome: | The proposed model outperforms existing methods with corpora of academic papers written in English by L1 Portuguese and L1 Spanish scholars and a reference corpus of expert academic English. |