From LLM to NMT: Advancing Low-Resource Machine Translation with Claude
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914764212404224 |
|---|---|
| author | Enis, Maxim Hopkins, Mark |
| author_facet | Enis, Maxim Hopkins, Mark |
| contents | We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. Though we find evidence of data contamination with Claude on FLORES-200, we curate new benchmarks that corroborate the effectiveness of Claude for low-resource machine translation into English. We find that Claude has remarkable \textit{resource efficiency} -- the degree to which the quality of the translation model depends on a language pair's resource level. Finally, we show that advancements in LLM translation can be compressed into traditional neural machine translation (NMT) models. Using Claude to generate synthetic data, we demonstrate that knowledge distillation advances the state-of-the-art in Yoruba-English translation, meeting or surpassing strong baselines like NLLB-54B and Google Translate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13813 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From LLM to NMT: Advancing Low-Resource Machine Translation with Claude Enis, Maxim Hopkins, Mark Computation and Language Artificial Intelligence We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. Though we find evidence of data contamination with Claude on FLORES-200, we curate new benchmarks that corroborate the effectiveness of Claude for low-resource machine translation into English. We find that Claude has remarkable \textit{resource efficiency} -- the degree to which the quality of the translation model depends on a language pair's resource level. Finally, we show that advancements in LLM translation can be compressed into traditional neural machine translation (NMT) models. Using Claude to generate synthetic data, we demonstrate that knowledge distillation advances the state-of-the-art in Yoruba-English translation, meeting or surpassing strong baselines like NLLB-54B and Google Translate. |
| title | From LLM to NMT: Advancing Low-Resource Machine Translation with Claude |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.13813 |