arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.02201cs.CL
收藏

低资源神经机器翻译的迁移学习

Transfer Learning for Low-Resource Neural Machine Translation

Information Sciences Institute, University of Southern California(南加州大学信息科学研究所);Koç University(科奇大学)

Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight

摘要:

神经机器翻译(NMT)的编码器-解码器框架在大数据场景中已经被证明是有效的,但对于低资源语言则不太有效。我们提出了一种迁移学习方法,该方法可以显着提高一系列低资源语言的Bleu分数。我们的核心思想是首先训练一个高资源的语言对(父模型),然后将一些学习到的参数转移到低资源对(子模型)来初始化和约束训练。使用我们的迁移学习方法,我们在四个低资源语言对上将基线NMT模型平均提高了5.6 Bleu。集成和未知词替换增加了另一个2 Bleu,这使得NMT在低资源机器翻译上的性能接近于基于强语法的机器翻译(SBMT)系统,超过了它在一个语言对上的性能。此外,使用迁移学习模型进行重新评分,我们可以将SBMT系统平均提高1.3 Bleu,提高低资源机器翻译的最新水平。

英文摘要:

The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we improve baseline NMT models by an average of 5.6 Bleu on four low-resource language pairs. Ensembling and unknown word replacement add another 2 Bleu which brings the NMT performance on low-resource machine translation close to a strong syntax based machine translation (SBMT) system, exceeding its performance on one language pair. Additionally, using the transfer learning model for re-scoring, we can improve the SBMT system by an average of 1.3 Bleu, improving the state-of-the-art on low-resource machine translation.

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。

↑