Mob Translate
Languages and libraries
translation engine
SHOW HN2020
How HN took it
4 positive, 9 neutral or asking, 0 mixed, 4 critical, out of 17 comments about the project. Thread score -0.01.
Idea: 1 for, 1 againstDocs: 0 for, 1 againstExecution: 0 for, 1 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Important initiative for language preservation
From 2 comments
Great initiative that will have significant impact by making translations available to all, including journalists, governmentS, lawyers, courts and merchants. And of course it…
wombatmobile on HNGreat project!
donbrae on HN
Helpful advice on OCR and Apertium
From 2 comments
> I will look into automating with OCR but it is also kind of cool to re-type it all to get a feel for the language myself. I ran the PDF through OCRmyPDF…
yorwba on HN> We have a dictionary in PDF form The file contains a copyright notice by the Summer Institute for Linguistics. That might cause legal trouble, although if the Australian…
yorwba on HN
Objections
Word-for-word replacement will not produce grammatical output
From 1 comment
Commendable effort, but do I understand correctly that you're just doing word-for-word replacements? If so, the end result will not be at all grammatical, since you're missing…
howlgarnish on HN
YAML is hard to edit and transform; XML is the field norm
From 1 comment
> into YAML Please reconsider this technical choice. YAML is a not only quite hard to edit manually, it's also difficult to transform automatically. I'm working in the dictionary…
tasogare on HN
Copyright in the SIL dictionary PDF may cause legal trouble
From 1 comment
> We have a dictionary in PDF form The file contains a copyright notice by the Summer Institute for Linguistics. That might cause legal trouble, although if the Australian…
yorwba on HN
ML approaches are poorly suited to these languages due to lack of data and context
From 1 comment
I think ML approaches are not well suited here - or at least there are still huge problems between non-germanic/Latin languages that have yet to be approached. (My background:…
akdor1154 on HN
Requests
Contributors and help with the dictionary transcription
From 1 comment
So the site is mostly a prototype at this point -> https://mobtranslate.com/ I'm building it out to be a fully open source and community driven project ->…
thomasfromcdnjs on HN
Use OCR instead of manual transcription
From 2 comments
> I will look into automating with OCR but it is also kind of cool to re-type it all to get a feel for the language myself. I ran the PDF through OCRmyPDF…
yorwba on HN> also kind of cool to re-type it all to get a feel for the language myself Don't. Or do, but in any event be really clear of your goals. Is your aim to get something done? Then…
throwaway_pdp09 on HN
Choose a more permissive license for the data
From 1 comment
If you are trying to promote usage of the data you might want to put the dictionary under a more permissive license as GPL-3+ conflicts with a lot of other licenses. Something…
E14n on HN
Questions
Resources and tips for writing a translation engine
From 1 comment
So the site is mostly a prototype at this point -> https://mobtranslate.com/ I'm building it out to be a fully open source and community driven project ->…
thomasfromcdnjs on HN
Alternatives named
Apertium
From 2 comments
> We have a dictionary in PDF form The file contains a copyright notice by the Summer Institute for Linguistics. That might cause legal trouble, although if the Australian…
yorwba on HNJust to mention, the Apertium community are very collaborative and always interested in all sort of minority languages, endangered and extinct languages and language revival. You…
anewhnaccount2 on HN
Google Translate
From 1 comment
Good effort, but this is not Google Translate, just Translate. Edit: I see the title of this post is changed now
rlv-dan on HN
Keyman
From 1 comment
> I will look into automating with OCR but it is also kind of cool to re-type it all to get a feel for the language myself. I ran the PDF through OCRmyPDF…
yorwba on HN