Does Neural Machine Translation Benefit from Larger Context?

Abstract

We propose a neural machine translation architecture that models the surrounding text in addition to the source sentence. These models lead to better performance, both in terms of general translation quality and pronoun prediction, when trained on small corpora, although this improvement largely disappears when trained with a larger corpus. We also discover that attention-based neural machine translation is well suited for pronoun prediction and compares favorably with other approaches that were specifically designed for this task.

References in corpus (1)

• Multimodal Attention for Neural Machine Translation

Cited by in corpus (35)

• Multilingual Denoising Pre-training for Neural Machine Translation
• Search Engine Guided Non-Parametric Neural Machine Translation
• Exploiting Cross-Sentence Context for Neural Machine Translation
• Using Whole Document Context in Neural Machine Translation
• A Comprehensive Survey of Grammar Error Correction
• Context-Aware Learning for Neural Machine Translation
• A Survey on Document-level Neural Machine Translation: Methods and Evaluation
• Neural Machine Translation: Challenges, Progress and Future
• Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models
• Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information
• Diverse Pretrained Context Encodings Improve Document Translation
• Towards Making the Most of Context in Neural Machine Translation
• A Comparison of Approaches to Document-level Machine Translation
• A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
• Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding
• Fill in the Blanks: Imputing Missing Sentences for Larger-Context Neural Machine Translation
• Chinese Poetry Generation with a Salient-Clue Mechanism
• When and Why is Document-level Context Useful in Neural Machine Translation?
• Document Graph for Neural Machine Translation
• Document-level Neural Machine Translation with Document Embeddings
• Context-Aware Neural Machine Translation Learns Anaphora Resolution
• Revisiting Context Choices for Context-aware Machine Translation
• Neural Machine Translation: A Review and Survey
• Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning
• Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model
• Do Context-Aware Translation Models Pay the Right Attention?
• Improving Context-aware Neural Machine Translation with Target-side Context
• Differentially Private Adapters for Parameter Efficient Acoustic Modeling
• Towards Fully Automated Manga Translation
• Context-Aware Monolingual Repair for Neural Machine Translation
• Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents
• Document-level Neural Machine Translation with Associated Memory Network
• Lexically Cohesive Neural Machine Translation with Copy Mechanism
• One Model to Learn Both: Zero Pronoun Prediction and Translation
• Reference Network for Neural Machine Translation