Learning to Parse and Translate Improves Neural Machine Translation

Abstract

There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a hybrid model, called NMT+RNNG, that learns to parse and translate by combining the recurrent neural network grammar into the attention-based neural machine translation. Our approach encourages the neural machine translation model to incorporate linguistic prior during training, and lets it translate on its own afterward. Extensive experiments with four language pairs show the effectiveness of the proposed NMT+RNNG.

Accepted as a short paper at the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)

References in corpus (5)

• Distilling the Knowledge in a Neural Network
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• On the difficulty of training Recurrent Neural Networks
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Neural Machine Translation with Source-Side Latent Graph Parsing

Cited by in corpus (10)

• Transforming Question Answering Datasets Into Natural Language Inference Datasets
• Search Engine Guided Non-Parametric Neural Machine Translation
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Predicting Target Language CCG Supertags Improves Neural Machine Translation
• Neural Machine Translation with Source-Side Latent Graph Parsing
• Inducing Grammars with and for Neural Machine Translation
• Graph-to-Sequence Learning using Gated Graph Neural Networks
• Discrete Structural Planning for Neural Machine Translation
• Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction
• Improving Multilingual Translation by Representation and Gradient Regularization