Papers by Jonathan Hus
Back to School: Translation Using Grammar Books (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current large language models require massive amounts of parallel sentences to perform machine translations for high resource languages. |
| Approach: | They propose to incorporate grammar books into the prompt of GPT-4 to improve machine translation and evaluate the performance on 16 topologically diverse low-resource languages. |
| Outcome: | The proposed method improves on 16 low-resource languages on 16 topologically diverse languages. |