Tied Multitask Learning for Neural Speech Translation

ACL 2018

Tied Multitask Learning for Neural Speech Translation

Jun 22, 2018
|
37 views
Details
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. Authors: Antonios Anastasopoulos, David Chiang (University of Notre Dame)

Comments
loading...