297 citations · 1.8k across the 50 of their papers we have counts for
7 papers · 2 filters
Fill in the Blanks: Imputing Missing Sentences for Larger-Context Neural Machine Translation
Sébastien Jean, Ankur Bapna, Orhan Firat
Most neural machine translation systems still translate sentences in isolation. To make further progress, a promising line of research additionally considers the surrounding contex…
Simple, Scalable Adaptation for Neural Machine Translation
Ankur Bapna, Naveen Arivazhagan, Orhan Firat
Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maint…
Investigating Multilingual NMT Representations at Scale
Sneha Reddy Kudugunta, Ankur Bapna, Isaac Caswell +2
Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly underst…
Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation
Aditya Siddhant, Melvin Johnson, Henry Tsai +5
The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a sin…
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Naveen Arivazhagan, Ankur Bapna, Orhan Firat +10
We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal…
The Missing Ingredient in Zero-Shot Neural Machine Translation
Naveen Arivazhagan, Ankur Bapna, Orhan Firat +3
Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they…
Non-Parametric Adaptation for Neural Machine Translation
Ankur Bapna, Orhan Firat
Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural…