A neural interlingua for multilingual machine translation
Authors:
- Yichao LuYLYichao Lu
- Phillip KeungPKPhillip Keung
- Faisal LadhakFLFaisal Ladhak
- Vikas BhardwajVBVikas Bhardwaj
- Shaonan ZhangSZShaonan Zhang
- Jason SunJSJason Sun
Preprint
Abstract
We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a true interlingua by performing direct zero-shot translation (without using pivot translation), and by using the interlingual sentence embeddings to train an English Yelp review classifier that, through the mediation of the interlingua, can also classify French and German reviews. Furthermore, we show that, despite using a smaller number of parameters than a pairwise collection of bilingual NMT models, our interlingual approach produces comparable BLEU scores for each language pair in WMT15.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A Teacher-Student Framework for Zero-Resource Neural Machine Translation2017
- Tree as a Pivot: Syntactic Matching Methods in Pivot Translation2017
- Zero-Resource Translation with Multi-Lingual Neural Machine Translation2016
- Neural Machine Translation of Rare Words with Subword Units2016
- Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism2016
- Multi-Task Learning for Multiple Language Translation2015
- On Using Very Large Target Vocabulary for Neural Machine Translation2015
- The United Nations Parallel Corpus v1.0