Neural Machine Translation with Source-Side Latent Graph Parsing
arXiv:1702.02265
Abstract
This paper presents a novel neural machine translation model which jointly learns translation and source-side latent graph representations of sentences. Unlike existing pipelined approaches using syntactic parsers, our end-to-end model learns a latent graph parser as part of the encoder of an attention-based neural machine translation model, and thus the parser is optimized according to the translation objective. In experiments, we first show that our model compares favorably with state-of-the-art sequential and pipelined syntax-based NMT models. We also show that the performance of our model can be further improved by pre-training it with a small amount of treebank annotations. Our final ensemble model significantly outperforms the previous best models on the standard English-to-Japanese translation dataset.
Accepted as a full paper at the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017)
References in corpus (8)
- Sequence to Sequence Learning with Neural Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Learning to Compose Words into Sentences with Reinforcement Learning
- Charagram: Embedding Words and Sentences via Character n-grams
- Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder
- Modeling Source Syntax for Neural Machine Translation
- Learning to Parse and Translate Improves Neural Machine Translation