The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task
Haque, RejwanulORCID: 0000-0003-1680-0099, Moslem, YasminORCID: 0000-0003-4595-6877 and Way, AndyORCID: 0000-0001-5736-5930
(2020)
The ADAPT system description for the STAPLE 2020 English-to-Portuguese translation task.
In: Fourth Workshop on Neural Generation and Translation (WNGT), Association for Computational Linguistics (ACL), 10 July 2020, Seattle, WA, USA (Online).
This paper describes the ADAPT Centre’s
submission to STAPLE (Simultaneous Translation and Paraphrase for Language Education) 2020, a shared task of the 4th Workshop on Neural Generation and Translation
(WNGT), for the English-to-Portuguese translation task. In this shared task, the participants were asked to produce high-coverage
sets of plausible translations given English
prompts (input source sentences). We present
our English-to-Portuguese machine translation
(MT) models that were built applying various strategies, e.g. data and sentence selection, monolingual MT for generating alternative translations, and combining multiple nbest translations. Our experiments show that
adding the aforementioned techniques to the
baseline yields an excellent performance in the
English-to-Portuguese translation task.
Science Foundation Ireland (SFI) Research Centres Programme (Grant No. 13/RC/2106), European Regional Development Fund, Research grants from SFI and Microsoft under Grant Numbers 13/RC/2077 and 18/CRT/6224
ID Code:
25447
Deposited On:
28 Jan 2021 14:12 by
Thomas Murtagh
. Last Modified 28 Jan 2021 14:12