-
Recent Posts
- Interesting case of first name disambiguation
- Superintelligent machine translation
- Writing differences between Corsican and Gallurese
- What are the conditions for a given endangered language to be a candidate for rule-based machine translation?
- Quandu da la forza à la raghjoni cuntrasta Tandu vinci la forza è la raghjoni ùn basta
Archives
Tags
adjective accordance Aesop citation conjugation Corsica Corsican 'sartinesu' Corsican language dependency parser dependency parsing dictionary diglossia diglossy disambiguation endangered languages false positive Feigenbaum hit Feigenbaum test French-Italian French into Corsican French to Corsican French to Corsican translation French to English French_Italian translator gaddhuresu Gallura gallurese gallurese language gender disambiguation Italian Italian language Jean de la Fontaine La Fontaine machine self-improvement machine translation might makes right numbers grammatical type past participe accordance philosophy of language policy rule-based machine translation self-reference semantic disambiguation statistical machine translation translation corpora translation corpus word-sense dismbiguation
Tag Archives: Corsican language
Interesting case of first name disambiguation
Here is an interesting case of first name disambiguation for machine translation. Consider the following first name ‘Camille’. It can apply to both genders. In Corsican (taravese or sartinese variants) it translates either into Cameddu (masculine) or Camedda (feminine). In … Continue reading
Writing differences between Corsican and Gallurese
Here are some writing differences between Corsican and Sardinian gallurese, that result from historical writing habits. These writing differences prevail, even when the words are the same: ghj is replaced by gghj: acciaghju (corsu), acciagghju (gallurese) , steel chj is … Continue reading
Posted in blog
Tagged Corsica, Corsican 'sartinesu', Corsican language, gaddhuresu, Gallura, gallurese, gallurese language, machine translation
Comments Off on Writing differences between Corsican and Gallurese
How rule-based and statistical machine translation can help each other
Here are a few suggestions on how rule-based and statistical machine translation can help each other: (This is a follow-up to the previous post) to begin with, rule-based and statistical machine translation are often contrasted and compared: it would be … Continue reading
Rough typology of remaining errors
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 of 95% performance should be attainable on the basis of correction of ‘easy’ tagged errors): … Continue reading
Posted in blog
Tagged Corsican language, machine translation
Comments Off on Rough typology of remaining errors
A first 100%!
Now scoring 1 – 0/124 = 100%. Translated into Corsican ‘sartinesu’. Another Feigenbaum hit.
