Attaining the unattainable? Reassessing claims
of human parity in neural machine translation
Toral, AntonioORCID: 0000-0003-2357-2960, Castilho, SheilaORCID: 0000-0002-8416-6555, Hu, Ke and Way, AndyORCID: 0000-0001-5736-5930
(2018)
Attaining the unattainable? Reassessing claims
of human parity in neural machine translation.
In: Third Conference on Machine Translation (WMT), 31 Oct- 1 Nov 2018, Brussels, Belgium.
ISBN 978-1-948087-81-0
We reassess a recent study (Hassan et al.,
2018) that claimed that machine translation
(MT) has reached human parity for the translation of news from Chinese into English, using
pairwise ranking and considering three variables that were not taken into account in that
previous study: the language in which the
source side of the test set was originally written, the translation proficiency of the evaluators, and the provision of inter-sentential context. If we consider only original source text
(i.e. not translated from another language, or
translationese), then we find evidence showing
that human parity has not been achieved. We
compare the judgments of professional translators against those of non-experts and discover that those of the experts result in higher
inter-annotator agreement and better discrimination between human and machine translations. In addition, we analyse the human translations of the test set and identify important
translation issues. Finally, based on these findings, we provide a set of recommendations for
future human evaluations of MT.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
e iADAATPA project funded by CEF research action (2016-EU-IA-0132) under grant agreement No.1331703, Science Foundation Ireland Research Centres Programme (Grant 13/RC/ 2106) and is co-funded under the European Regional Development Fund
ID Code:
23081
Deposited On:
13 Mar 2019 12:25 by
Thomas Murtagh
. Last Modified 20 Jan 2021 16:48