Conference paper Open Access

KIT's Submission to the IWSLT 2019 Shared Task on Text Translation

Schneider, Felix; Waibel, Alex

In this paper, we describe KIT’s submission for the IWSLT 2019 shared task on text translation. Our system is based on the transformer model [1] using our in-house implementation. We augment the available training data using back-translation and employ fine-tuning for the final model. For our best results, we used a 12-layer transformer-big config- uration, achieving state-of-the-art results on the WMT2018 test set. We also experiment with student-teacher models to improve performance of smaller models.

Files (95.6 kB)
Name Size
IWSLT2019_paper_30.pdf
md5:5e830364de4b52bbdbe9d55348d8bba2
95.6 kB Download
139
94
views
downloads
All versions This version
Views 139138
Downloads 9494
Data volume 9.0 MB9.0 MB
Unique views 125124
Unique downloads 8888

Share

Cite as