Sparse moe with language guided routing for multilingual machine translation
Sparse Mixture-of-Experts (SMoE) has gained increasing popularity as a promising
framework for scaling up multilingual machine translation (MMT) models with negligible …
framework for scaling up multilingual machine translation (MMT) models with negligible …
Improving zero-shot multilingual neural machine translation by leveraging cross-lingual consistency regularization
The multilingual neural machine translation (NMT) model has a promising capability of zero-
shot translation, where it could directly translate between language pairs unseen during …
shot translation, where it could directly translate between language pairs unseen during …
On the off-target problem of zero-shot multilingual neural machine translation
While multilingual neural machine translation has achieved great success, it suffers from the
off-target issue, where the translation is in the wrong language. This problem is more …
off-target issue, where the translation is in the wrong language. This problem is more …
UM4: unified multilingual multiple teacher-student model for zero-resource neural machine translation
Most translation tasks among languages belong to the zero-resource translation problem
where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) …
where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) …
Towards a better understanding of variations in zero-shot neural machine translation performance
Multilingual Neural Machine Translation (MNMT) facilitates knowledge sharing but often
suffers from poor zero-shot (ZS) translation qualities. While prior work has explored the …
suffers from poor zero-shot (ZS) translation qualities. While prior work has explored the …
Informative language representation learning for massively multilingual neural machine translation
In a multilingual neural machine translation model that fully shares parameters across all
languages, an artificial language token is usually used to guide translation into the desired …
languages, an artificial language token is usually used to guide translation into the desired …
Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation
Although existing multilingual neural machine translation (MNMT) models have
demonstrated remarkable performance to handle multiple translation directions in a single …
demonstrated remarkable performance to handle multiple translation directions in a single …
Unlikelihood tuning on negative samples amazingly improves zero-shot translation
Zero-shot translation (ZST), which is generally based on a multilingual neural machine
translation model, aims to translate between unseen language pairs in training data. The …
translation model, aims to translate between unseen language pairs in training data. The …
Exploring the impact of layer normalization for zero-shot neural machine translation
This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation
(ZST). Recent efforts for ZST often utilize the Transformer architecture as the backbone, with …
(ZST). Recent efforts for ZST often utilize the Transformer architecture as the backbone, with …
Adaptive token-level cross-lingual feature mixing for multilingual neural machine translation
Multilingual neural machine translation aims to translate multiple language pairs in a single
model and has shown great success thanks to the knowledge transfer across languages …
model and has shown great success thanks to the knowledge transfer across languages …