arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.02745cs.CL
收藏

用于Few-Shot NMT适应的元学习

Meta-Learning for Few-Shot NMT Adaptation

University of Maryland(马里兰大学);Microsoft(微软);Microsoft Research(微软研究院)

Amr Sharaf, Hany Hassan, Hal Daumé

摘要:

我们提出了META-MT,一种元学习方法,用于在Few-Shot设置中适应神经机器翻译(NMT)系统。META-MT提供了一种新的方法,使NMT模型可以很容易地适应许多目标领域的最小量的域内数据。我们将NMT系统的自适应框架视为元学习问题,在该问题中,我们基于模拟的离线元训练领域自适应任务来学习适应新的未知领域。我们评估了建议的元学习策略上的10个领域与一般的大规模NMT系统。我们表明,META-MT显着优于经典的领域自适应时,很少的域中的例子。我们的实验表明,META-MT在只看到4000个翻译单词(300个平行句子)的情况下,可以比经典的微调高出2.5个BLEU点。

英文摘要:

We present META-MT, a meta-learning approach to adapt Neural Machine Translation (NMT) systems in a few-shot setting. META-MT provides a new approach to make NMT models easily adaptable to many target domains with the minimal amount of in-domain data. We frame the adaptation of NMT systems as a meta-learning problem, where we learn to adapt to new unseen domains based on simulated offline meta-training domain adaptation tasks. We evaluate the proposed meta-learning strategy on ten domains with general large scale NMT systems. We show that META-MT significantly outperforms classical domain adaptation when very few in-domain examples are available. Our experiments shows that META-MT can outperform classical fine-tuning by up to 2.5 BLEU points after seeing only 4, 000 translated words (300 parallel sentences).

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。

↑