KoBE: Knowledge-Based Machine Translation Evaluation

Zorik Gekhman, Roee Aharoni, Genady Beryozkin, Markus Freitag, Wolfgang Macherey


Abstract
We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a large-scale multilingual knowledge base, and (2) measuring the recall of the grounded entities found in the candidate vs. those found in the source. Our approach achieves the highest correlation with human judgements on 9 out of the 18 language pairs from the WMT19 benchmark for evaluation without references, which is the largest number of wins for a single evaluation method on this task. On 4 language pairs, we also achieve higher correlation with human judgements than BLEU. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data.
Anthology ID:
2020.findings-emnlp.287
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3200–3207
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.287
DOI:
10.18653/v1/2020.findings-emnlp.287
Bibkey:
Cite (ACL):
Zorik Gekhman, Roee Aharoni, Genady Beryozkin, Markus Freitag, and Wolfgang Macherey. 2020. KoBE: Knowledge-Based Machine Translation Evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3200–3207, Online. Association for Computational Linguistics.
Cite (Informal):
KoBE: Knowledge-Based Machine Translation Evaluation (Gekhman et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2020.findings-emnlp.287.pdf
Video:
 https://slideslive.com/38940035
Code
 zorikg/KoBE