Conference paper Open Access

CMU's Machine Translation System for IWSLT 2019

Srinivasan, Tejas; Sanabria, Ramon; Metze, Florian

In Neural Machine Translation (NMT) the usage of sub-􏰃words and characters as source and target units offers a simple and flexible solution for translation of rare and unseen􏰃 words. However, selecting the optimal subword segmentation involves a trade-off between expressiveness and flexibility, and is language and dataset-dependent. We present Block Multitask Learning (BMTL), a novel NMT architecture that predicts multiple targets of different granularities simulta- neously, removing the need to search for the optimal seg- mentation strategy. Our multi-task model exhibits improvements of up to 1.7 BLEU points on each decoder over single-task baseline models with the same number of parameters on datasets from two language pairs of IWSLT15 and one from IWSLT19. The multiple hypotheses generated at different granularities can also be combined as a post-processing step to give better translations.

Files (844.0 kB)
Name Size
IWSLT2019_paper_33.pdf
md5:c3dcd0b82c35d844e7fcb4a2ae05bde1
844.0 kB Download
0
0
views
downloads
All versions This version
Views 00
Downloads 00
Data volume 0 Bytes0 Bytes
Unique views 00
Unique downloads 00

Share

Cite as