Modelling source- and target-language syntactic Information as
conditional context in interactive neural machine translation
Gupta, Kamal Kumar, Haque, RejwanulORCID: 0000-0003-1680-0099, Ekbal, Asif, Bhattacharyya, Pushpak and Way, AndyORCID: 0000-0001-5736-5930
(2020)
Modelling source- and target-language syntactic Information as
conditional context in interactive neural machine translation.
In: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2-6 Nov 2020, Lisboa, Portugal.
In interactive machine translation (MT),
human translators correct errors in auto-
matic translations in collaboration with the
MT systems, which is seen as an effective
way to improve the productivity gain in
translation. In this study, we model source-
language syntactic constituency parse and
target-language syntactic descriptions in
the form of supertags as conditional con-
text for interactive prediction in neural
MT (NMT). We found that the supertags
significantly improve productivity gain in
translation in interactive-predictive NMT
(INMT), while syntactic parsing somewhat
found to be effective in reducing human
efforts in translation. Furthermore, when
we model this source- and target-language
syntactic information together as the con-
ditional context, both types complement
each other and our fully syntax-informed
INMT model shows statistically significant
reduction in human efforts for a French–
to–English translation task in a reference-
simulated setting, achieving 4.30 points
absolute (corresponding to 9.18% relative)
improvement in terms of word prediction
accuracy (WPA) and 4.84 points absolute
(corresponding to 9.01% relative) reduc-
tion in terms of word stroke ratio (WSR)
over the baseline.
Proceedings of the 22nd Annual Meeting of the European Association for Machine Translation, (EAMT 2020).
.
European Association for Machine Translation (EAMT).
Publisher:
European Association for Machine Translation (EAMT)
TDIL, MeiTY, Govt. of India for the project ”Hindi to English Machine Translation for Judicial Domain [11(3)/2015-HCC(TDIL], Science Foundation Ireland (SFI) Research Centres Programme (Grant No. 13/RC/2106) and is cofunded under the European Regional Development Fund
ID Code:
24420
Deposited On:
30 Apr 2020 12:32 by
Rejwanul Haque
. Last Modified 10 Mar 2021 12:26