Tied Multitask Learning for Neural Speech Translation

Antonios Anastasopoulos, David Chiang


Abstract
We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task, since higher-level intermediate representations should provide useful information. Second, we apply regularization that encourages transitivity and invertibility. We show that the application of these notions on jointly trained models improves performance on the tasks of low-resource speech transcription and translation. It also leads to better performance when using attention information for word discovery over unsegmented input.
Anthology ID:
N18-1008
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
82–91
Language:
URL:
https://www.aclweb.org/anthology/N18-1008
DOI:
10.18653/v1/N18-1008
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N18-1008.pdf
Video:
 http://vimeo.com/276441141