To improve the performance of Neural Machine Translation~(NMT) for
low-resource languages~(LRL), one effective strategy is to leverage parallel
data from a related high-resource language~(HRL). However, multilingual data
has been found more beneficial for NMT models that translate from the LRL to a
target language than the ones that translate into the LRLs. In this paper, we
aim to improve the effectiveness of multilingual transfer for NMT models that
translate \emph{into} the LRL, by designing a better decoder word embedding.
Extending upon a general-purpose multilingual encoding method Soft Decoupled
Encoding~\citep{SDE}, we propose DecSDE, an efficient character n-gram based
embedding specifically designed for the NMT decoder. Our experiments show that
DecSDE leads to consistent gains of up to 1.8 BLEU on translation from English
to four different languages.

本文探讨了在低资源语言翻译中，利用高资源语言数据进行多语言转移的方法，通过提出一种基于字符 N-gram 的嵌入方法 DecSDE，使得从英语到四种不同语言的翻译 BLEU 值提高了最高 1.8 个百分点。

增强多语言神经机器翻译中目标侧词汇转移

Improving Target-side Lexical Transfer in Multilingual Neural Machine  Translation

We improve automatic correction of grammatical, orthographic, and collocation
errors in text using a multilayer convolutional encoder-decoder neural network.
The network is initialized with embeddings that make use of character N-gram
information to better suit this task. When evaluated on common benchmark test
data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior
neural approaches on this task as well as strong statistical machine
translation-based systems with neural and task-specific features trained on the
same data. Our analysis shows the superiority of convolutional neural networks
over recurrent neural networks such as long short-term memory (LSTM) networks
in capturing the local context via attention, and thereby improving the
coverage in correcting grammatical errors. By ensembling multiple models, and
incorporating an N-gram language model and edit features via rescoring, our
novel method becomes the first neural approach to outperform the current
state-of-the-art statistical machine translation-based approach, both in terms
of grammaticality and fluency.

本研究提出了一种基于多层卷积编码 - 解码神经网络的自动文本纠错方法，利用字符 N-gram 信息来初始化 embeddings，通过 attention 机制捕捉局部文本语境并使用 N-gram 语言模型和编辑特征进行打分和融合，实现了比现有基于统计学习的方法更好的语法和流畅度的纠错效果。