Category Archives: blog

One hundred users for the Traduttore corsu app for Android

The Traduttore corsu application for Android has now more than a hundred users. Moving on…

Posted in blog | Tagged , , | Leave a comment

More on polymorphic disambiguation…

Let’s take another look at polymorphic disambiguation. We shall consider the French word sequence ‘nombre de’. The translation into Corsican (the same goes for English and other languages) cannot be identical, because ‘number of’ can be translated in two different … Continue reading

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

Performing our first open test of the year

Let us comment on the remaining errors encountered in the above open test: French ‘carrière’ remains undisambiguated: either carriera (career) or cava (quarry): two occurrences ‘de’: French ‘de’ is perhaps the most difficult word to translate into another language, due … Continue reading

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

More on the remaining 1% problem

The analysis of the Wikipedia article of the day in French is interesting, in the sense that it sheds light on the skills that will be necessary for a machine translation system to achieve a 100% accurate translation. The error … Continue reading

Posted in blog | Tagged , | 1 Comment

More on two-sided grammar

Let us expand the idea of two-sided (from the analytic/synthetic duality standpoint) grammatical analysis: consider, for example, ‘beaucoup et souvent’ (a lot and often) in the sentence ‘il mange beaucoup et souvent’ (he eats a lot and often). Analytically, ‘beaucoup … Continue reading

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

New version on Android Playstore

The application now changes its name on the Android Playstore, and becomes “Traduttore corsu”: the name is not very original, let’s face it, but at least it is easy to understand. “Traduttore corsu” is dedicated especially to the translation from … Continue reading

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

Some advance in polymorphic disambiguation

Just powered the new engine (prototypal, not yet transferred to the API which is used both by the current site translator and the Android application) and made a few tests: it works! Let us take an example with French ‘en … Continue reading

Posted in blog | Leave a comment

Follow-up to Autonomous MT system

Closely related to my previous post on autonomous MT systems is the article on the fact that Researchers have developed a machine-learning system capable of deciphering lost languages.

Posted in blog | Leave a comment

Autonomous MT system

Let us speculate about what could be an autonomous MT system. In the present state of MT we provide rules and dictionary to the software (rules-based translation) or we feed it with a corpus regarding a given pair of languages … Continue reading

Posted in blog | Tagged , , | 1 Comment

On the statistical/rule-based divide regarding MT

The classical divide with regard to MT separates statistical from rule-based MT. But this divide is not as clear-cut as one could think at first glance. For rule-based MT can operate statistically. Let us take an example, concerning the disambiguation … Continue reading

Posted in blog | Tagged , | Leave a comment

Priority pairs for endangered languages

Let us discuss the question of priority pairs with regard to endangered languages. It consists of the most wanted translation pairs for a given endangered language, in keeping with the main language with which it is associated. To take an … Continue reading

Posted in blog | Tagged , | 1 Comment

More on two-sided grammatical analysis

Let us give some further examples of two-sided grammatical analysis: “à dessein” (purposedly), “à volonté” (at will), “à tort” (mistakenly): from an analytical standpoint, these are prepositions followed by a singular noun. From a synthetical viewpoint, they are adverbs (adverbial … Continue reading

Posted in blog | Tagged , , | 1 Comment

Two-sided grammatical analysis

Let us call two-sided grammatical analysis the type of grammatical analysis that will be described below. Two-sided grammatical analysis contrasts with one-sided analysis, which sees a sequence of words either as a locution type (adverbial locution, verbal locution, noun locution, … Continue reading

Posted in blog | Tagged , , | 1 Comment

A hard case for disambiguation: polymorphic disambiguation

Let us investigate an issue that relates to disambiguation. It is a hard case that needs to be addressed: I shall call it in what follows, for reasons that will become clearer later, polymorphic disambiguation. Let us take an example. … Continue reading

Posted in blog | Tagged | 1 Comment

Some ethics for MT related to endangered languages

Let us sketch what could be some ethical requirements related to machine translation regarding endangered languages. Perhaps a first requirement would be: don’t publish translation pairs regarding an endangered language until the success rate has reached at least 90%. Because … Continue reading

Posted in blog | Leave a comment

Word sense disambiguation: a hard case

Let us consider a hard case for word sense disambiguation, in the context of French to Corsican MT. But the same goes for French to English MT. It relates to French words such as: ‘accomplit’, ‘affaiblit’, ‘affranchit’, ‘alourdit’, ‘amortit’. The … Continue reading

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

More on grammatical type disambiguation

Let us focus on grammatical type disambiguation, which is a subproblem of word disambiguation. General grammatical types are: verbs, nouns, adjectives, adverbs, prepositions, gerundive, etc. But for grammatical type disambiguation purposes, more accuracy is in order: instances of grammatical types … Continue reading

Posted in blog | Tagged , , | Comments Off on More on grammatical type disambiguation

New insight on the issue of pair reversal (updated)

The issue of pair reversal: it goes as follows: Suppose your have a given translation pair A>B that translates language A into language B, how hard is it to build the reverse pair B>A? Now the current instance of this … Continue reading

Posted in blog | Tagged , , | Comments Off on New insight on the issue of pair reversal (updated)

How to translate ‘Cette phrase est en français’ ? (This sentence is in French) – updated

Let us consider the following French sentence: Le comté de Kronoberg est un comté suédois dont le nom signifie en français ‘Couronne de montagne’. It translates into Corsican: A cuntea di Kronoberg hè una cuntea svedese chì u so nome significheghja in … Continue reading

Posted in blog | Tagged , , , | Comments Off on How to translate ‘Cette phrase est en français’ ? (This sentence is in French) – updated

What is required from Artificial General Intelligence with regard to Machine Translation?

We will be interested in a series of posts to try to define what is required of an AGI (Artificial General Intelligence) in order to reach the level of superintelligence in MT (machine translation). (All this is highly speculative, but … Continue reading

Posted in blog | Tagged , , , , | Comments Off on What is required from Artificial General Intelligence with regard to Machine Translation?

Follow-up to the ‘issue of pair reversal’ and first steps for Italian to Corsican

Here is a short follow-up to the ‘issue of pair reversal’ regarding language pairs. It seems some 90% could be achieved in this reversal process. What is lacking here is an adequate handling of disambiguation. Let us focus on one … Continue reading

Posted in blog | Comments Off on Follow-up to the ‘issue of pair reversal’ and first steps for Italian to Corsican

Superintelligent machine translation (updated)

Let us consider superintelligence with regard to machine translation. To fix ideas, we can propose a rough definition: it consists of a machine with the ability to translate with 99% (or above) accuracy from one of the 8000 languages to … Continue reading

Posted in blog | Tagged , , , , , , , , , , , | Comments Off on Superintelligent machine translation (updated)

New open test

Performing now a new open test, with the first 100 (more or less) words of the ‘article of the day’ from French wikipedia: we get 94,02% = 1 – (8 / 134). Several errors (5) result from lack of vocabulary. … Continue reading

Posted in blog | Comments Off on New open test

Minor breakthrough

It is kind of a minor breakthrough. The translation of French ‘en même temps que’ (at the same time as) is somewhat hard, in that it can take two different forms: either à tempu à or à tempu ch’è, depending on the context. The … Continue reading

Posted in blog | Comments Off on Minor breakthrough

Priority pairs regarding endangered languages

There exists priority translation pairs, from the standpoint of endangered languages. Such notion of a priority pair (the most useful pair for the current users of the endangered language), regarding a given endangered language. For example, French to Corsican is … Continue reading

Posted in blog | Tagged | Comments Off on Priority pairs regarding endangered languages

Should machine translation software go open source

There is an ongoing debate on whether AI software should go open source or not (for example Bostrom’s paper Strategic Implications of Openness in AI Development). Now our current concern is of whether MT software should go open source or … Continue reading

Posted in blog | Comments Off on Should machine translation software go open source

Some thoughts on the remaining 1% problem

To begin with, let us state the 1% problem, for machine translation: it seems some 99% accuracy in machine translation could be attainable but the remaining 1% (1% is just a given number, somewhat arbitrarily chosen, but useful to to … Continue reading

Posted in blog | Tagged , | Leave a comment

Just powered the new grammatical engine

Just powered the new grammatical engine: it seems to allow for some interesting things, notably related to expressions. The case at hand is the French expression “parler comme un moulin”  (talk the leg off a chair) that translates into Corsican … Continue reading

Posted in blog | Tagged | Comments Off on Just powered the new grammatical engine

Is rule-based MT more ethical than statistical MT?

In the ongoing debate on safe IA, it is a relevant open question of whether rule-based MT is more ethical than statistical MT. Here are some arguments in favor of rule-based MT in this context (without blaming statistical MT which has its … Continue reading

Posted in blog | Tagged , , , , , | Comments Off on Is rule-based MT more ethical than statistical MT?

Open test – october 18 , 2018

Performing now an open test (now fully ‘open’ since it can be verified via https://okchakko.com/translate), from the 100 first words of the daily article of French wikipedia. There is one full sentence, but some remaining errors: dopu à quattordici anni brama di … Continue reading

Posted in blog | Leave a comment