The ISC is part of the Johns Hopkins Applied Physics Laboratory and will follow all current policies. Please visit the JHU/APL page for more information on the Lab's visitor guidance.

2019

Curriculum Learning for Domain Adaptation in Neural Machine Translation


Abstract

We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a particular schedule. This approach is simple to implement on top of any neural framework or architecture, and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language pairs.

Citation

@inproceedingszhang-etal-2019-curriculum title: "Curriculum Learning for Domain Adaptation in Neural Machine Translation" author: "Zhang Xuan and Shapiro Pamela and Kumar Gaurav and McNamee Paul and Carpuat Marine and Duh Kevin" booktitle: "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1 (Long and Short Papers)" month: jun year: "2019" address: "Minneapolis Minnesota" publisher: "Association for Computational Linguistics" url: "https://www.aclweb.org/anthology/N19-1189" doi: "10.18653/v1/N19-1189" pages: "1903--1915" abstract: "We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a particular schedule. This approach is simple to implement on top of any neural framework or architecture and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language pairs."

Citation

@inproceedingszhang-etal-2019-curriculum title: "Curriculum Learning for Domain Adaptation in Neural Machine Translation" author: "Zhang Xuan and Shapiro Pamela and Kumar Gaurav and McNamee Paul and Carpuat Marine and Duh Kevin" booktitle: "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1 (Long and Short Papers)" month: jun year: "2019" address: "Minneapolis Minnesota" publisher: "Association for Computational Linguistics" url: "https://www.aclweb.org/anthology/N19-1189" doi: "10.18653/v1/N19-1189" pages: "1903--1915" abstract: "We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a particular schedule. This approach is simple to implement on top of any neural framework or architecture and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language pairs."