资源分类
》 资源 》论文》Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation

Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation

2019-09-19 | |  208 |   63 |   0 0 0
Abstract We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). We propose and test two methods for augmenting NMT training data with fuzzy TM matches. Tests on the DGTTM data set for two language pairs show consistent and substantial improvements over a range of baseline systems. The results suggest that this method is promising for any translation environment in which a sizeable TM is available and a certain amount of repetition across translations is to be expected, especially considering its ease of implementation

上一篇：Monotonic Infinite Lookback Attention for Simultaneous Machine Translation

下一篇：Putting Evaluation in Context: Contextual Embeddings improve Machine Translation Evaluation

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

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