Rethinking Document-level Neural Machine Translation
Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Shujian Huang, Jiajun Chen, Lei Li · Findings of the Association for Computational Linguistics: ACL 2022 · 2022
This paper does not aim at introducing a novel model for document-level neural machine translation.Instead, we head back to the original Transformer model and hope to answer the following question: Is the capacity of current models strong enough for documentlevel translation?Interestingly, we observe that the original Transformer with appropriate training techniques can achieve strong results for document translation, even with a length of 2000 words.We evaluate this model and several recent approaches on nine documentlevel datasets and two sentence-level datasets across six languages.Experiments show that document-level Transformer models outperforms sentence-level ones and many previous methods in a comprehensive set of metrics, including BLEU, four lexical indices, three newly proposed assistant linguistic indicators, and human evaluation.Our new datasets and evaluation scripts are in https://github. com/sunzewei2715/Doc2Doc_NMT.