Neural Machine Translation with External Phrase Memory
arXiv:1606.01792
Abstract
In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. The phraseNet not only approaches one step towards incorporating external knowledge into neural machine translation, but also makes an effort to extend the word-by-word generation mechanism of recurrent neural network. Our empirical study on Chinese-to-English translation shows that, with carefully-chosen phrase table in memory, phraseNet yields 3.45 BLEU improvement over the generic neural machine translator.
8 figures, 9 pages
References in corpus (7)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Modeling Coverage for Neural Machine Translation
- Neural Summarization by Extracting Sentences and Words
- Noisy Activation Functions
- Encoding Source Language with Convolutional Neural Network for Machine Translation
- Neural Generative Question Answering
Cited by in corpus (20)
- Code-Switching for Enhancing NMT with Pre-Specified Translation
- Interactive Attention for Neural Machine Translation
- Guiding Neural Machine Translation with Retrieved Translation Pieces
- Unsupervised Neural Machine Translation with SMT as Posterior Regularization
- Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
- Translating Phrases in Neural Machine Translation
- Phrase-Based Attentions
- Improving Neural Machine Translation through Phrase-based Forced Decoding
- Neural Phrase-to-Phrase Machine Translation
- Neural Machine Translation Advised by Statistical Machine Translation
- Neural Entity Reasoner for Global Consistency in NER
- Paying Attention to Multi-Word Expressions in Neural Machine Translation
- Merging External Bilingual Pairs into Neural Machine Translation
- Latent Relation Language Models
- Sequential Copying Networks
- Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
- Phrase Table as Recommendation Memory for Neural Machine Translation
- Neural Machine Translation: A Review and Survey
- EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints
- Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT