This example shows how to make translations with DeepL more “context aware”.
If you have several strings which you translate in isolation, each for themselves, DeepL will need to guess their meaning.
For example for the word “table”, DeepL will assume a “a table of numbers”, and not a piece of furniture. However, if you have a context, such as “table and chair”, DeepL will be able to deduct the proper meaning.
If you need to translate a bunch of single words or short texts (e.g. for internationalization aka. i18n of your software products or websites), it makes sense to combine them into one bigger text which improves the ability for DeepL to detect the proper context.
This workflow demonstrates how to combine a table with input strings into a larger XML string, translate it in one go, and then split the text back into the input rows.
This idea was suggested by Tim Cadenbach, DeepL - thank you very much!
To use this workflow in KNIME, download it from the below URL and open it in KNIME:
Download WorkflowDeploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.
Try NodePit Runner!Do you have feedback, questions, comments about NodePit, want to support this platform, or want your own nodes or workflows listed here as well? Do you think, the search results could be improved or something is missing? Then please get in touch! Alternatively, you can send us an email to mail@nodepit.com, follow @NodePit on Twitter or botsin.space/@nodepit on Mastodon.
Please note that this is only about NodePit. We do not provide general support for KNIME — please use the KNIME forums instead.