A neural interlingua for multilingual machine translation

Abstract

We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a language-independent representation by performing direct zero-shot translation (without using pivot translation), and by using the source sentence embeddings to create an English Yelp review classifier that, through the mediation of the neural 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 approach produces comparable BLEU scores for each language pair in WMT15.

arXiv commentAccepted in WMT 18

References in corpus (4)

• Convolutional Sequence to Sequence Learning
• Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
• A Teacher-Student Framework for Zero-Resource Neural Machine Translation
• Effective Strategies in Zero-Shot Neural Machine Translation

Cited by in corpus (9)

• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Multilingual NMT with a language-independent attention bridge
• (Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation
• Learning Shared Semantic Space for Speech-to-Text Translation
• A Survey on Low-Resource Neural Machine Translation
• Towards Interlingua Neural Machine Translation
• Revisiting Modularized Multilingual NMT to Meet Industrial Demands
• Self-Learning for Zero Shot Neural Machine Translation