Most existing machine translation systems operate at the level of words,
relying on explicit segmentation to extract tokens. We introduce a neural
machine translation (NMT) model that maps a source character sequence to a
target character sequence without any segmentation. We employ a character-level
convolutional network with max-pooling at the encoder to reduce the length of
source representation, allowing the model to be trained at a speed comparable
to subword-level models while capturing local regularities. Our
character-to-character model outperforms a recently proposed baseline with a
subword-level encoder on WMT'15 DE-EN and CS-EN, and gives comparable
performance on FI-EN and RU-EN. We then demonstrate that it is possible to
share a single character-level encoder across multiple languages by training a
model on a many-to-one translation task. In this multilingual setting, the
character-level encoder significantly outperforms the subword-level encoder on
all the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality
of the multilingual character-level translation even surpasses the models
specifically trained on that language pair alone, both in terms of BLEU score
and human judgment.

该研究提出了一个无需分词的神经机器翻译模型，在 WMT'15 数据集上使用多语言字符级编码器和基于字符卷积神经网络的模型，不仅速度快，泛化性能好，而且能够跨多语言实现高质量普适翻译，效果优于子词级编码器。

不需显式分段的全字符级神经机器翻译

Fully Character-Level Neural Machine Translation without Explicit  Segmentation

The existing machine translation systems, whether phrase-based or neural,
have relied almost exclusively on word-level modelling with explicit
segmentation. In this paper, we ask a fundamental question: can neural machine
translation generate a character sequence without any explicit segmentation? To
answer this question, we evaluate an attention-based encoder-decoder with a
subword-level encoder and a character-level decoder on four language
pairs--En-Cs, En-De, En-Ru and En-Fi-- using the parallel corpora from WMT'15.
Our experiments show that the models with a character-level decoder outperform
the ones with a subword-level decoder on all of the four language pairs.
Furthermore, the ensembles of neural models with a character-level decoder
outperform the state-of-the-art non-neural machine translation systems on
En-Cs, En-De and En-Fi and perform comparably on En-Ru.

本文探讨了使用字符级别的解码器和子词级别的编码器在神经网络机器翻译中能否生成一个不需要显式分段的字符序列，并使用 WMT'15 平行语料库对四种语言对 - En-Cs、En-De、En-Ru 和 En-Fi 进行了实验，结果表明具有字符级别解码器的模型在所有四种语言对上的表现均优于具有子词级别解码器的模型，在 En-Cs、En-De 和 En-Fi 上的神经网络插件比最先进的非神经机器翻译系统更为优秀，在 En-Ru 上性能相当。