资源分类
》 资源 》论文》Domain Adaptive Inference for Neural Machine Translation

Domain Adaptive Inference for Neural Machine Translation

2019-09-19 | |  88 |   51 |   0 0 0
Abstract We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sacrificing performance on the original domain. We adapt sequentially across two SpanishEnglish and three English-German tasks, comparing unregularized fine-tuning, L2 and Elastic Weight Consolidation. We then report a novel scheme for adaptive NMT ensemble decoding by extending Bayesian Interpolation with source information, and show strong improvements across test domains without access to the domain label.

上一篇：Disentangled Representation Learning for Non-Parallel Text Style Transfer

下一篇：Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...