English

Multilingual Neural Machine Translation with Task-Specific Attention

Computation and Language 2018-06-11 v1

Abstract

Multilingual machine translation addresses the task of translating between multiple source and target languages. We propose task-specific attention models, a simple but effective technique for improving the quality of sequence-to-sequence neural multilingual translation. Our approach seeks to retain as much of the parameter sharing generalization of NMT models as possible, while still allowing for language-specific specialization of the attention model to a particular language-pair or task. Our experiments on four languages of the Europarl corpus show that using a target-specific model of attention provides consistent gains in translation quality for all possible translation directions, compared to a model in which all parameters are shared. We observe improved translation quality even in the (extreme) low-resource zero-shot translation directions for which the model never saw explicitly paired parallel data.

Keywords

Cite

@article{arxiv.1806.03280,
  title  = {Multilingual Neural Machine Translation with Task-Specific Attention},
  author = {Graeme Blackwood and Miguel Ballesteros and Todd Ward},
  journal= {arXiv preprint arXiv:1806.03280},
  year   = {2018}
}

Comments

COLING 2018

R2 v1 2026-06-23T02:23:58.777Z