On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, Steffen Eger


Abstract
Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual textual similarity. In this paper, we concern ourselves with reference-free machine translation (MT) evaluation where we directly compare source texts to (sometimes low-quality) system translations, which represents a natural adversarial setup for multilingual encoders. Reference-free evaluation holds the promise of web-scale comparison of MT systems. We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER. We find that they perform poorly as semantic encoders for reference-free MT evaluation and identify their two key limitations, namely, (a) a semantic mismatch between representations of mutual translations and, more prominently, (b) the inability to punish “translationese”, i.e., low-quality literal translations. We propose two partial remedies: (1) post-hoc re-alignment of the vector spaces and (2) coupling of semantic-similarity based metrics with target-side language modeling. In segment-level MT evaluation, our best metric surpasses reference-based BLEU by 5.7 correlation points.
Anthology ID:
2020.acl-main.151
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1656–1671
Language:
URL:
https://aclanthology.org/2020.acl-main.151
DOI:
10.18653/v1/2020.acl-main.151
Bibkey:
Cite (ACL):
Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, and Steffen Eger. 2020. On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1656–1671, Online. Association for Computational Linguistics.
Cite (Informal):
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation (Zhao et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.acl-main.151.pdf
Video:
 http://slideslive.com/38929444
Code
 AIPHES/ACL20-Reference-Free-MT-Evaluation