Adapting Large Language Models for Document-Level Machine Translation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912068569923584 |
|---|---|
| author | Wu, Minghao Vu, Thuy-Trang Qu, Lizhen Foster, George Haffari, Gholamreza |
| author_facet | Wu, Minghao Vu, Thuy-Trang Qu, Lizhen Foster, George Haffari, Gholamreza |
| contents | Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs. We first investigate the impact of prompt strategies on translation performance and then conduct extensive experiments using two fine-tuning methods, three LLM backbones, and 18 translation tasks across nine language pairs. Our results show that specialized models can sometimes surpass GPT-4 in translation performance but still face issues like off-target translation due to error propagation in decoding. We provide an in-depth analysis of these LLMs tailored for DocMT, examining translation errors, discourse phenomena, strategies for training and inference, the data efficiency of parallel documents, recent test set evaluations, and zero-shot crosslingual transfer. Our findings highlight the strengths and limitations of LLM-based DocMT models and provide a foundation for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06468 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adapting Large Language Models for Document-Level Machine Translation Wu, Minghao Vu, Thuy-Trang Qu, Lizhen Foster, George Haffari, Gholamreza Computation and Language Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses on adapting LLMs for document-level machine translation (DocMT) for specific language pairs. We first investigate the impact of prompt strategies on translation performance and then conduct extensive experiments using two fine-tuning methods, three LLM backbones, and 18 translation tasks across nine language pairs. Our results show that specialized models can sometimes surpass GPT-4 in translation performance but still face issues like off-target translation due to error propagation in decoding. We provide an in-depth analysis of these LLMs tailored for DocMT, examining translation errors, discourse phenomena, strategies for training and inference, the data efficiency of parallel documents, recent test set evaluations, and zero-shot crosslingual transfer. Our findings highlight the strengths and limitations of LLM-based DocMT models and provide a foundation for future research. |
| title | Adapting Large Language Models for Document-Level Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.06468 |