CLApr 23, 2018

A neural interlingua for multilingual machine translation

arXiv:1804.08198v31144 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of efficient and language-independent translation for multilingual NLP applications, though it is incremental as it builds on existing NMT methods.

The authors tackled the problem of multilingual machine translation by incorporating a neural interlingua into an encoder-decoder architecture, achieving comparable BLEU scores on WMT15 language pairs with fewer parameters than bilingual models and enabling zero-shot translation and cross-lingual classification.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes