Exploiting Cross-Sentence Context for Neural Machine Translation
arXiv:1704.04347
Abstract
In translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a cross-sentence context-aware approach and investigate the influence of historical contextual information on the performance of neural machine translation (NMT). First, this history is summarized in a hierarchical way. We then integrate the historical representation into NMT in two strategies: 1) a warm-start of encoder and decoder states, and 2) an auxiliary context source for updating decoder states. Experimental results on a large Chinese-English translation task show that our approach significantly improves upon a strong attention-based NMT system by up to +2.1 BLEU points.
References in corpus (5)
Cited by in corpus (14)
- Multilingual Denoising Pre-training for Neural Machine Translation
- A Survey of Deep Learning Techniques for Neural Machine Translation
- A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
- Search Engine Guided Non-Parametric Neural Machine Translation
- Context-Aware Self-Attention Networks
- Context-Aware Learning for Neural Machine Translation
- Learning to Remember Translation History with a Continuous Cache
- Diverse Pretrained Context Encodings Improve Document Translation
- A Comparison of Approaches to Document-level Machine Translation
- Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding
- Learning to Discriminate Noises for Incorporating External Information in Neural Machine Translation
- Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism
- Chinese-Portuguese Machine Translation: A Study on Building Parallel Corpora from Comparable Texts
- Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation