An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation

被引：83

作者：

Chu, Chenhui ^{[1
,3
]}

Dabre, Raj ^{[2
]}

Kurohashi, Sadao ^{[2
]}

机构：

[1] Osaka Univ, Inst Databil Sci, Suita, Osaka, Japan

[2] Kyoto Univ, Grad Sch Informat, Kyoto, Japan

[3] Japan Sci & Technol Agcy, Kawaguchi, Saitama, Japan

来源：

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2 | 2017年

关键词：

D O I：

10.18653/v1/P17-2061

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper, we propose a novel domain adaptation method named "mixed fine tuning" for neural machine translation (NMT). We combine two existing approaches namely fine tuning and multi domain NMT. We first train an NMT model on an out-of-domain parallel corpus, and then fine tune it on a parallel corpus which is a mix of the in-domain and out-of-domain corpora. All corpora are augmented with artificial tags to indicate specific domains. We empirically compare our proposed method against fine tuning and multi domain methods and discuss its benefits and shortcomings.

引用

页码：385 / 391

页数：7