Capturing Longer Context for Document-level Neural Machine Translation: A Multi-resolutional Approach
Preprint
Abstract
Discourse context has been proven useful when translating documents. It is quite a challenge to incorporate long document context in the prevailing neural machine translation models such as Transformer. In this paper, we propose multi-resolutional (MR) Doc2Doc, a method to train a neural sequence-to-sequence model for document-level translation. Our trained model can simultaneously translate sentence by sentence as well as a document as a whole. We evaluate our method and several recent approaches on nine document-level datasets and two sentence-level datasets across six languages. Experiments show that MR Doc2Doc outperforms sentence-level models and 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 25 references indexed in Scilit:
- 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
- A Simple and Effective Unified Encoder for Document-Level Machine Translation2020
- 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
- Document-Level Neural Machine Translation with Hierarchical Attention Networks2018
- Improving the Transformer Translation Model with Document-Level Context2018
- Exploiting Cross-Sentence Context for Neural Machine Translation2017
- Rethinking the Inception Architecture for Computer Vision2016
- Dropped pronoun generation for dialogue machine translation2016