Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models
Transactions of the Association for Computational Linguistics · 07.01.2025 · 13 · 73-95
DOI: 10.1162/tacl_a_00730 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 07.01.2025. Verfasst von Jianhui Pang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The evolution of Neural Machine Translation (NMT) has been significantly influenced by six core challenges (Koehn and Knowles, 2017) that have acted as benchmarks for progress in this field. This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models (LLMs): domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search. Our empirical findings show that LLMs effectively reduce reliance on parallel data for major languages during pretraining and significantly improve translation of long sentences containing approximately 80 words, even translating documents up to 512 words. Despite these improvements, challenges in domain mismatch and rare word prediction persist. While NMT-specific challenges like word alignment and beam search may not apply to LLMs, we identify three new challenges in LLM-based translation: inference efficiency, translation of low-resource languages during pretraining, and human-aligned evaluation.
Zitieren
APA
Pang, J., Ye, F., Wong, D. F., Yu, D., Shi, S., Tu, Z., & Wang, L. (2025). Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models. Transactions of the Association for Computational Linguistics, 13, 73-95. https://doi.org/10.1162/tacl_a_00730
Vancouver
Pang J, Ye F, Wong DF, Yu D, Shi S, Tu Z, et al. Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models. Transactions of the Association for Computational Linguistics. 2025;13:73-95. doi:10.1162/tacl_a_00730
BibTeX
@article{Pang2025,
author = {Pang, Jianhui and Ye, Fanghua and Wong, Derek Fai and Yu, Dian and Shi, Shuming and Tu, Zhaopeng and Wang, Longyue},
title = {Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models},
journal = {Transactions of the Association for Computational Linguistics},
year = {2025},
volume = {13},
pages = {73--95},
doi = {10.1162/tacl_a_00730}
}
EUVIMED