arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.06147cs.CLcs.LG
收藏

神经机器翻译中的无显式分割解码器

A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation

Université de Montréal(蒙特利尔大学);New York University(纽约大学)

Junyoung Chung, Kyunghyun Cho, Yoshua Bengio

摘要:

现有的机器翻译系统,无论是基于短语的还是神经的,几乎完全依赖于具有显式分割的词级建模。在本文中,我们提出了一个基本问题:神经机器翻译可以生成一个字符序列,而无需任何显式分割?为了回答这个问题,我们使用WMT'15的并行语料库评估了基于注意力的编码器-解码器,该编码器-解码器具有子字级编码器和字符级解码器,用于四种语言对-En-Cs,En-De,En-Ru和En-Fi。我们的实验表明,在所有四种语言对上,具有字符级解码器的模型都优于具有子词级解码器的模型。此外,具有字符级解码器的神经模型的集合在En-Cs、En-De和En-Fi上的性能优于最先进的非神经机器翻译系统,并且在En-Ru上进行了翻译。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑