تقرير
Dynamically Composing Domain-Data Selection with Clean-Data Selection by 'Co-Curricular Learning' for Neural Machine Translation
العنوان: | Dynamically Composing Domain-Data Selection with Clean-Data Selection by 'Co-Curricular Learning' for Neural Machine Translation |
---|---|
المؤلفون: | Wang, Wei, Caswell, Isaac, Chelba, Ciprian |
المصدر: | The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019) |
سنة النشر: | 2019 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Machine Learning |
الوصف: | Noise and domain are important aspects of data quality for neural machine translation. Existing research focus separately on domain-data selection, clean-data selection, or their static combination, leaving the dynamic interaction across them not explicitly examined. This paper introduces a "co-curricular learning" method to compose dynamic domain-data selection with dynamic clean-data selection, for transfer learning across both capabilities. We apply an EM-style optimization procedure to further refine the "co-curriculum". Experiment results and analysis with two domains demonstrate the effectiveness of the method and the properties of data scheduled by the co-curriculum. Comment: 11 pages |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/1906.01130 |
رقم الأكسشن: | edsarx.1906.01130 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |