The Open Innovation Team ran a two week experiment with SUMO localizers to understand if introducing machine translation could improve the current workflow, the contributor experience and make it easier to have top priority articles covered with less effort.
The results were very satisfactory. By the end of the experiment 62 of the 72 articles were fully translated. We attracted 2 new contributors and volunteers reported an overall satisfaction score of 4.75/7. While there is lots more to learn and experiment with, these results suggest experimenting with adding mechanisms, like machine translation, into traditional workflows can save localizers a lot of time and cover many pending articles.
Due to SUMO forums syntax limitations, I have posted the full report on discourse, keep reading to learn more!
https://discourse.mozilla.org/t/sumo-localization-experiment-report/41407
Thanks!
The Open Innovation Team ran a two week experiment with SUMO localizers to understand if introducing machine translation could improve the current workflow, the contributor experience and make it easier to have top priority articles covered with less effort.
The results were very satisfactory. By the end of the experiment 62 of the 72 articles were fully translated. We attracted 2 new contributors and volunteers reported an overall satisfaction score of 4.75/7. While there is lots more to learn and experiment with, these results suggest experimenting with adding mechanisms, like machine translation, into traditional workflows can save localizers a lot of time and cover many pending articles.
Due to SUMO forums syntax limitations, I have posted the full report on discourse, keep reading to learn more!
https://discourse.mozilla.org/t/sumo-localization-experiment-report/41407
Thanks!
Using the machine translation as a starter is OK, but Google Translate is far from perfect. Perhaps you could try a different engine, for instance https://www.deepl.com.
Using the machine translation as a starter is OK, but Google Translate is far from perfect. Perhaps you could try a different engine, for instance https://www.deepl.com.
We evaluated different providers before we started the experiment (including deepl) and Google Cloud Translate v3 (which is different from google translate web) provided a more consistent quality across different locales.
But as I explained in the report, we'll need to do a per-locale analysis to decide the best provider for each.
We evaluated different providers before we started the experiment (including deepl) and Google Cloud Translate v3 (which is different from google translate web) provided a more consistent quality across different locales.
But as I explained in the report, we'll need to do a per-locale analysis to decide the best provider for each.
'''[[Firefox for Fire TV|Firefox for fire TV]] ''''
Rubén Martín said
We evaluated different providers before we started the experiment (including deepl) and Google Cloud Translate v3 (which is different from google translate web) provided a more consistent quality across different locales.
But as I explained in the report, we'll need to do a per-locale analysis to decide the best provider for each.
''Rubén Martín [[#post-76109|said]]''
<blockquote>
We evaluated different providers before we started the experiment (including deepl) and Google Cloud Translate v3 (which is different from google translate web) provided a more consistent quality across different locales.
But as I explained in the report, we'll need to do a per-locale analysis to decide the best provider for each.
</blockquote>
