Category Archives: blog

What are the conditions for a given endangered language to be a candidate for rule-based machine translation?

What are the conditions for a given endangered language to be a candidate for rule-based machine translation? For a given endangered language to be a candidate for rule-based machine translation, some requirements are in order. There is notably need for: a … Continue reading

Posted in blog | Tagged , , , , , , , , , | Comments Off on What are the conditions for a given endangered language to be a candidate for rule-based machine translation?

Weekly open test

Weekly open test: 1 – (6/128) = 95,31%. It should read U righjimentu cumprendi instead of capisci.

Posted in blog | Leave a comment

Solving fivefold ambiguity: translation for French ‘poste’

French word ‘poste’ has (at least) fivefold ambiguity. For it can designate: ‘poste’ (masculine singular noun) : postu, masculine singular noun (set, i.e. television set) ‘poste’ (masculine singular noun): posta, feminine singular noun (position): erroneously translated as postu in the present case … Continue reading

Posted in blog | Tagged , , , | Leave a comment

Open test: december 2, 2017

Weekly open test: scoring 1 – (1/114) = 99.12%. Of interest: ‘Four swords’ remains properly untranslated, and ‘four’ (fornu/forru in Corsican, oven in English) is left as is.

Posted in blog | Leave a comment

Rough typology of remaining errors (updated)

French to Corsican: performing on French wikipedia sample test currently amounts to 93% on average. Below is a rough typology of remaining errors (presumably an average scoring of 95% on the open test should be attainable on the basis of correction … Continue reading

Posted in blog | Tagged , | Leave a comment