Neural Machine Translation with Source-Side Latent Graph Parsing
Neural Machine Translation with Source-Side Latent Graph Parsing
复制标题
DOI：
10.18653/v1/d17-1012
复制
发表时间：
2017-02
期刊：
影响因子：
--
通讯作者：
Kazuma Hashimoto;Yoshimasa Tsuruoka
中科院分区：
文献类型：
--
作者：
Kazuma Hashimoto;Yoshimasa Tsuruoka
本文提出了一种新的神经机器翻译模型，该模型联合学习句子的翻译和源侧潜图表示。与现有的使用句法解析器的流水线方法不同，我们的端到端模型学习潜在图解析器作为基于注意力的神经机器翻译模型的编码器的一部分，从而根据翻译目标对解析器进行优化。在实验中，我们首先证明了我们的模型比目前最先进的基于顺序和流水线语法的NMT模型要好得多。我们还表明，通过使用少量的树库注释对模型进行预训练，可以进一步提高模型的性能。我们最终的系综模型在标准的英语到日语翻译数据集上的表现明显优于之前的最佳模型。
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.