Coverage Embedding Models for Neural Machine Translation

Abstract

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a full coverage embedding vector to track the coverage status, and then keeps updating it with neural networks as the translation goes. Experiments on the large-scale Chinese-to-English task show that our enhanced model improves the translation quality significantly on various test sets over the strong large vocabulary NMT system.

6 pages; In Proceddings of EMNLP 2016

References in corpus (3)

• ADADELTA: An Adaptive Learning Rate Method
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Supervised Attentions for Neural Machine Translation

Cited by in corpus (19)

• Get To The Point: Summarization with Pointer-Generator Networks
• Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
• One Sentence One Model for Neural Machine Translation
• Memory-augmented Neural Machine Translation
• Deconvolution-Based Global Decoding for Neural Machine Translation
• Decoding-History-Based Adaptive Control of Attention for Neural Machine Translation
• Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
• Source-side Prediction for Neural Headline Generation
• Improving Neural Machine Translation through Phrase-based Forced Decoding
• Neural Machine Translation with Key-Value Memory-Augmented Attention
• Multi-Domain Dialogue Acts and Response Co-Generation
• Towards Decoding as Continuous Optimization in Neural Machine Translation
• Coupling Distributed and Symbolic Execution for Natural Language Queries
• Modeling Future Cost for Neural Machine Translation
• Neural Text Generation with Artificial Negative Examples
• English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor
• Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations
• Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation
• Future-Prediction-Based Model for Neural Machine Translation