Neural Phrase-to-Phrase Machine Translation

Abstract

In this paper, we propose Neural Phrase-to-Phrase Machine Translation (NP${}^2$MT). Our model uses a phrase attention mechanism to discover relevant input (source) segments that are used by a decoder to generate output (target) phrases. We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018). Furthermore, our method can naturally integrate with external phrase dictionaries during decoding. Empirical experiments show that our method achieves comparable performance with the state-of-the art methods on benchmark datasets. However, when the training and testing data are from different distributions or domains, our method performs better.

References in corpus (6)

• Convolutional Sequence to Sequence Learning
• An Actor-Critic Algorithm for Sequence Prediction
• Segmental Recurrent Neural Networks
• Neural Machine Translation with External Phrase Memory
• Multitask Learning with CTC and Segmental CRF for Speech Recognition
• Phrase-Based Attentions

Cited by in corpus (5)

• Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection
• MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
• Identifying extra high frequency gravitational waves generated from oscillons with cuspy potentials using deep neural networks
• Alleviate Exposure Bias in Sequence Prediction \\ with Recurrent Neural Networks
• Neural Machine Translation: A Review and Survey