Zero Shot Translation
Related Papers
Improving Zero-Shot Translation of Low-Resource Languages
AbstractRecent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zero-shot) translation directions not observed at training time. We …...
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
AbstractZero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, …...
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
AbstractUnsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for …...
Sparse and Decorrelated Representations for Stable Zero-shot NMT
AbstractUsing a single encoder and decoder for all directions and training with English-centric data is a popular scheme for multilingual NMT. However, zero-shot translation under this scheme is vulnerable to …...
Improving Zero-Shot Translation by Disentangling Positional Information
AbstractMultilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output …...
Language Tags Matter for Zero-Shot Neural Machine Translation
Multilingual Neural Machine Translation (MNMT) has aroused widespread interest due to its efficiency. An exciting advantage of MNMT models is that they could also translate between unsupervised (zero-shot) language directions. …...
Learning Language Specific Sub-network for Multilingual Machine Translation
AbstractMultilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration …...
Adapting to Non-Centered Languages for Zero-shot Multilingual Translation
AbstractMultilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination …...
Informative Language Representation Learning for Massively Multilingual Neural Machine Translation
AbstractIn 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 target language. However, …...
Multilingual Neural Machine Translation With the Right Amount of Sharing
AbstractLarge multilingual Transformer-based machine translation models have had a pivotal role in making translation systems available for hundreds of languages with good zero-shot translation performance. One such example is the …...
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation
AbstractThis paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source …...
Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation
AbstractMultilingual neural translation models exploit cross-lingual transfer to perform zero-shot translation between unseen language pairs. Past efforts to improve cross-lingual transfer have focused on aligning contextual sentence-level representations. This paper …...