Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
arXiv:1811.01100
Abstract
Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation. We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model. Experiments on Chinese-English translation show that our approach leads to significant improvements.
arXiv commentACL 2017 (modified)
References in corpus (9)
- Sequence to Sequence Learning with Neural Networks
- ADADELTA: An Adaptive Learning Rate Method
- Modeling Coverage for Neural Machine Translation
- Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
- Neural Machine Translation with External Phrase Memory
- Coverage Embedding Models for Neural Machine Translation
- Incorporating Discrete Translation Lexicons into Neural Machine Translation
- Neural Machine Translation Advised by Statistical Machine Translation
- Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora
Cited by in corpus (5)
- Glyce: Glyph-vectors for Chinese Character Representations
- Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
- Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization
- Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
- A Survey on Knowledge integration techniques with Artificial Neural Networks for seq-2-seq/time series models