It is of course biased by the communication channel that is used (diary). For example I am quite active in the German forum and on the Italian mailing list and telegram channel (all in local language), but all diary posts I have made were in English because it is the language I expected would have the farest reach, and those diary posts were not intended for a specific local audience.
4 Likes
I looked into the DeepL thing a bit.
-
I found out why this fork is not merged: See DeepL integration for Translator plugin - marketplace - Discourse Meta and DeepL support for Discourse Translator - #28 by koen360 - feature - Discourse Meta . Summary: DeepL API is a bit dicey according to the plugin author and the fork is not in a state to merge it. The author estimated that it would take at least $500 to get it to a state where it could be merged. The issue @cquest encountered with that the plugin creates too many API calls is known and there is no workaround for it it looks like.
-
The Ruby library GitHub - peterc/whatlanguage: A language detection library for Ruby that uses bloom filters for speed. to detect languages is 15 years old and hasn’t been updated much since then, the number of languages it supports is very limited. It is documented to work only well with posts that are long enough (longer than a twitter post). So, if the translator plugin was modified to do the language detection locally with that library, it will probably never be merged upstream due these limitations.
Given these two things, using the DeepL-fork of the translator plugin sounds a bit dicey to me. I don’t know what is missing in the DeepL fork, but given the amount the author estimated to finish it, I don’t have a good feeling about this. If we don’t get DeepL to sponsor us, the possible solutionss to workaround the “too many API calls” issue sound really dicey to me.
Do you have a source for this?
LibreTranslate is an API and web-app built on top of Argos Translate.
Here are the vailable models: Argos Open Tech
All of them (unless I missed one) are from or to english.
Another option is to use LibreTranslate which seems to support language detection…
I’m quite sure that with all the available tools we have, this plugin can be improved to better fit our needs.
I see that Bing has been mentioned as an option. They are an OSMF corporate member so might be open to sponsoring this. The named contact on the OSMF Advisory Board is Harsh Govind. Let me know if you’d like me to send him an email.
2 Likes
@RobJN I’m not sure if there is anyone participating in this thread who would have the authority to say to go ahead but you could ask tentatively (de:unverbindlich - “without obligation”?) - like @cquest did for DeepL.
If Microsoft would sponsor automatic translation in this forum, I think it would be the best and easiest solution because:
- Bing has pretty much complete language coverage
- Discourse Translator plugin can be used out of the box, basically no effort for the admins (unlike for DeepL where that fork with rough edges needs to be used and probably some sort of workaround be implemented)
- From the few that tried Bing translation so far, it sounded like the translation quality was reasonably good, apparently better than Google and maybe even on par with DeepL
3 Likes
Mir entzieht sich die Notwendigkeit einer maschinellen Übersetzung noch, nach ein wenig Überlegungen. Wer soll das alles lesen, wenn die ganze Welt sich an einem Thema abarbeitet? Mir scheint es ausreichend, wenn die Sprache des Topics maschinell erkannt werden kann. Dann können der Sprache Mächtige sich damit beschäftigen. Zusätzliche Hinweise, um was es geht, dienen natürlich dem Zweck, dann könnten nur Leute angesprochen werden, die in der Sache Bescheid wissen, usw. Kurz gesagt, Übersetzung ein Extra, Erkennung wünschenswert.
Mir entzieht sich die Notwendigkeit einer maschinellen Übersetzung noch, nach ein wenig Überlegungen. Wer soll das alles lesen, wenn die ganze Welt sich an einem Thema abarbeitet?
sicherlich wird man kaum alles lesen, aber derzeit finden defacto die meisten Diskussionen z.B. zur tag-Findung auf englisch statt, und wenn man das nicht versteht ist man auf Übersetzung angewiesen oder ausgeschlossen. Ähnlich auch bei Themen zur policy, und allgemein alles auf internationaler Ebene.
ENGLISH translation:
Nobody will read everything, but as most of the discussion about tagging and other topics (policy) etc. is in English, people who do not understand English are depending on automatic translation or are excluded from participating.
1 Like
@Hungerburg @dieterdreist It would be appreciated if you can post in English (even using a machine translation site) in topics that are already being discussed in this language. The forum doesn’t have yet capabilities to provide translation of your messages and it would help people here to understand you.
Thanks!
2 Likes
As has been noted elsewhere (numerous times) it isn’t always possible to get the same nuance in a “lingua franca” as it is in a native language. I think it’s important that when (as here) a number of the contributions are writing in one language (German) that they be incouraged to write in that language first, and then perhaps add a machine translation below.
Several very active OSM communities around the world contain relatively few fluent English speakers; to restrict them from contributing to threads like this seems like a bad idea.
2 Likes
Yes, the ask is to provide at least the English translation of their posts so people reading this topic can follow.
This seems like a good guideline for this multilingual forum.
- Always feel free to post in your native language
- When replying to a thread in a language differing from the original post, it is polite to also include a translation (machine or otherwise) of your text into the OP language.
5 Likes
Maybe it was late and I was tired, as its now; Writing can be exhausting, to get everything right, writing in a foreign language is not the same as translating, it is thinking in a foreign language, and that does not make the task any easier.
Maybe this incident can be seen as a preview of what a truly multilingual forum will face. From toying around with what machine translation offers, I guess, I will have to adapt my writing a bit, to get a translation, that meets my expectations. This for English, no idea about languages that I have no command of in the least.
Implementation challenges: When I post in native language, will the post appear as English to me/others? Will it appear in whatever language my or their user agent (aka web-browser) claims? Will the source language text be shown in a tooltip on mouseover?
Information challenges: As a user, I think I’d not have time, to follow a category, where people from all over the world post topics, that I get to read translated. Machine translation surely makes life easier for moderators, but does it the same for users, that want to provide “Help and support” e.g?
On the controversial post above: Maybe language detection brings us a big part of what translation can do. If the OP (topic opener) sets the language of the topic, a tag can do that, preferably in the language and script gathered. So people can subscribe to receive posts to some category in some language.
(In case, this garners little attention, they can always try and post in a lingua franca, that might get them a wider audience.)
3 Likes
Yes, I agree, communication in foreign languages is not easy and often associated with misunderstandings. But these can usually be cleared up easily if there is a benevolent effort on all sides.
The upcoming internationalisation of communication is undoubtedly a challenge for the community. For me, it is an ongoing process in which solutions can be tried out and also discarded if it turns out that they don’t work. And with Discourse there is a powerful tool available that should enable us to realize this flexible approach.
2 Likes
I have installed the discourse translation extension. I have enabled Azure (Microsoft) as the translation provider.
Please update this thread with any feedback.
PS: The little “world” icon at the bottom of a non-UI language post is the translate button.
11 Likes
Will it be monitored how much it is used after a few weeks so that the price doesn’t explode without noticing (and we have an estimate how much it will cost in the future)?
1 Like
Yes, I will check in a few weeks the cost. I have $200 free available for 1 year in Azure.
My first impression is really good.
Even if my first trial dutch->French is as suboptimal as I would have expected with a machine translation, I had my little ‘wow’ effect. Good job!
One have to be logged in, any way to default to English for non logged in user?