Searching for a Higher Power in the Human Evaluation of MT

Johnny Wei, Tom Kocmi, Christian Federmann


Abstract
In MT evaluation, pairwise comparisons are conducted to identify the better system. In conducting the comparison, the experimenter must allocate a budget to collect Direct Assessment (DA) judgments. We provide a cost effective way to spend the budget, but show that typical budget sizes often do not allow for solid comparison. Taking the perspective that the basis of solid comparison is in achieving statistical significance, we study the power (rate of achieving significance) on a large collection of pairwise DA comparisons. Due to the nature of statistical estimation, power is low for differentiating less than 1-2 DA points, and to achieve a notable increase in power requires at least 2-3x more samples. Applying variance reduction alone will not yield these gains, so we must face the reality of undetectable differences and spending increases. In this context, we propose interim testing, an “early stopping” collection procedure that yields more power per judgment collected, which adaptively focuses the budget on pairs that are borderline significant. Interim testing can achieve up to a 27% efficiency gain when spending 3x the current budget, or 18% savings at the current evaluation power.
Anthology ID:
2022.wmt-1.7
Volume:
Proceedings of the Seventh Conference on Machine Translation (WMT)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Philipp Koehn, Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Tom Kocmi, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri, Aurélie Névéol, Mariana Neves, Martin Popel, Marco Turchi, Marcos Zampieri
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
129–139
Language:
URL:
https://aclanthology.org/2022.wmt-1.7
DOI:
Bibkey:
Cite (ACL):
Johnny Wei, Tom Kocmi, and Christian Federmann. 2022. Searching for a Higher Power in the Human Evaluation of MT. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 129–139, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Searching for a Higher Power in the Human Evaluation of MT (Wei et al., WMT 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wmt-1.7.pdf
Video:
 https://aclanthology.org/2022.wmt-1.7.mp4