Rethinking Document-level Neural Machine Translation
Preprint
Abstract
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 document-level 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 document-level 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.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Multilingual Denoising Pre-training for Neural Machine TranslationTransactions of the Association for Computational Linguistics, 2020
- Better Document-Level Machine Translation with Bayes’ RuleTransactions of the Association for Computational Linguistics, 2020
- Improving Context-Aware Neural Machine Translation Using Self-Attentive Sentence EmbeddingProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation2020
- A Simple and Effective Unified Encoder for Document-Level Machine Translation2020
- Modeling Coherence for Discourse Neural Machine TranslationProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Learning to Remember Translation History with a Continuous CacheTransactions of the Association for Computational Linguistics, 2018
- Translating Pro-Drop Languages With Reconstruction ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Rethinking the Inception Architecture for Computer Vision2016
- Dropped pronoun generation for dialogue machine translation2016