Evaluation of translation quality assessment metrics (blind)
The task is to investigate metrics for automatic evaluation of machine translation results or other similar data types. [ver. 2.0.4]
poleval-2021 mt quality-estimation
Git repo URL: https://github.com/poleval/2021-quality-estimation-blind / Branch: main
Run git clone --single-branch https://github.com/poleval/2021-quality-estimation-blind -b main to get the challenge data
Browse at https://github.com/poleval/2021-quality-estimation-blind/tree/main
Leaderboard
| # | submitter | when | ver. | description | test-A Pearson | test-B Pearson | × | |
|---|---|---|---|---|---|---|---|---|
| 1 | eNeLPol UJ AGH | 2021-09-01 09:39 | 2.0.2 poleval-2021 | B1 | N/A | 0.5138 | 4 | |
| 2 | skok.ai | 2021-09-06 17:35 | 2.0.2 poleval-2021 | blind score v016 | N/A | 0.4840 | 26 | |
| 3 | Adam Mickiewicz University | 2021-08-29 11:39 | 2.0.2 poleval-2021 | C-01 | N/A | 0.4793 | 10 |