UScore: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation

Jonas Belouadi, Steffen Eger


Abstract
The vast majority of evaluation metrics for machine translation are supervised, i.e., (i) are trained on human scores, (ii) assume the existence of reference translations, or (iii) leverage parallel data. This hinders their applicability to cases where such supervision signals are not available. In this work, we develop fully unsupervised evaluation metrics. To do so, we leverage similarities and synergies between evaluation metric induction, parallel corpus mining, and MT systems. In particular, we use an unsupervised evaluation metric to mine pseudo-parallel data, which we use to remap deficient underlying vector spaces (in an iterative manner) and to induce an unsupervised MT system, which then provides pseudo-references as an additional component in the metric. Finally, we also induce unsupervised multilingual sentence embeddings from pseudo-parallel data. We show that our fully unsupervised metrics are effective, i.e., they beat supervised competitors on 4 out of our 5 evaluation datasets. We make our code publicly available.
Anthology ID:
2023.eacl-main.27
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
358–374
Language:
URL:
https://aclanthology.org/2023.eacl-main.27
DOI:
10.18653/v1/2023.eacl-main.27
Award:
 EACL Outstanding Paper
Bibkey:
Cite (ACL):
Jonas Belouadi and Steffen Eger. 2023. UScore: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 358–374, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
UScore: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation (Belouadi & Eger, EACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.eacl-main.27.pdf
Software:
 2023.eacl-main.27.software.zip
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2023.eacl-main.27.mp4