Disambiguation is an essential process in machine translation. Sometimes, however, it seems more rational and logical to leave an ambiguity in the translation. This is the case when (i) there is an ambiguous word in the sentence to be translated; and (ii) the context does not provide an objective reason to choose one of the two occurrences. It seems that in this case, the best translation is the one that leaves the ambiguity intact.
Let’s take an example. Consider the following French sentence: ‘Son palais était en feu.’. The French word ‘palais’ is ambiguous, because it corresponds in English and in Corsican to two different words (palace, palazzu and palate, palatu).
Thus, we have 3 possibilities of translation:
His palate was on fire
His palace was on fire
His palace/palate was on fire
The third translation, in my opinion, is better, because it points out that the context is insufficient to choose one of the two alternatives.
Consider now, on the one hand, the following sentence: ‘Il avait mangé du piment fort. Son palais était en feu.’ Now the context provides an objective motivation to choose one of the two occurence. This yields the following translation: He had eaten some hot pepper. His palate was on fire.
On the other hand, consider the following sentence: ‘Les ennemis du prince avaient lancé des engins incendiaires. Son palais était en feu.’ We also have here an objective reason to choose the other alternative. It translates then: The prince’s enemies had thrown incendiary devices. His palace was on fire.
What are the characteristics we want for an AGI (artificial general intelligence)? An AGI should have a very advanced capacity in NLP and language comprehension. One of the qualities we expect from an AGI is respect for multilingualism. Hopefully, the AGI should have extensive NLP capabilities, which apply to a large number of languages, and even to the 8000 languages of the planet, i.e. also to the 90% of endangered languages. The AGI could thus help to solve an important problem inherent to the problem of language extinction, which affects human cultural diversity (it can be assumed that some languages will be extinct at the time of the AGI event, but the AGI could thus help to revitalize them).
Let us expand the idea of text analysis derived from rule-based translation. Above is an example of a classic word-based search. In this particular case, it is the French word ‘été’. This word is ambiguous because it can be a common noun (‘summer’), or a past participle (‘been’). Below is an example of a search for the word ‘summer’ associated with the grammatical type ‘common noun’.
Conditional search based on ‘noun’ grammatical type
Finally, we have below an example of a search for the word ‘summer’ associated with the grammatical type ‘past participle’.
Conditional search based on ‘past participle’ grammatical type
Rule-based translation is difficult to implement. The main difficulty encountered is taking into account the groups of words, so as to be on a par with statistics-based translation. The main problems in this regard are (i) polymorphic disambiguation; and (ii) building a fair typology of grammatical types. But once these steps begin to be mastered, there are many advantages. What seems essential here is that with the same piece of software, both machine translation and text analysis can be carried out. Among the modules that are easy to implement are the following:
lemmatizer
part-of-speech tagger
singularizer
pluralizer
grammar checker
type extractor: a module that allows you to extract words from a text according to their grammatical category
For the implementation of rule-based translation provides the machine with some inherent understanding of the text, in the same way that a human being does. To put it in a nutshell, it is better artificial intelligence.
Finally, other modules, more advanced, seem possible (to be confirmed).
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 that appears here is characteristic and must probably be placed in the missing 1% to achieve 100% accuracy in the translation (the problem of the remaining 1%). The phrase ‘Her father studied at the University of Oregon and then at Yale Law School‘ has a definite article with elision: l’. The translation given (u/a, i.e. indeterminate between the masculine definite article u and the feminine definite article a) is not correct in that it fails to determine the gender – masculine or feminine – of Yale Law School, the name of an English school. In order to provide the correct translation, it is necessary to know how to translate Yale Law School into Corsican, and thus to determine that school is translated by scola, which is feminine. Therefore the correct translation should have been: po à a Yale Law School prima di …. This finally shows that a translator capable of translating with 100% performance must be able (i) to determine the language in which the text parts are written in another language and (ii) to translate those text parts into the target language. This highlights the skills necessary to successfully achieve the remaining 1% are: (i) the ability to determine the language of a subtext and (ii) the ability to translate a subtext from any language in the target language.
Presently, we can only conjecture that this ability to solve the remaining 1% requires artificial general intelligence (AGI ). Now providing concrete and detailed examples may help to confirm or disprove that hypothesis.
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 we shall give it a try.) One of the difficulties that arise in machine translation relates to the translation of expressions. This leads us to mention one of the required skills of a superintelligence. It is the ability to identify an expression within a text in a given language and then to translate it into another language. Let us mention that expressions are of different types: verbal, nominal, adjectival, adverbial, … To fix the ideas we can focus here on verbal expressions. For example, the French expression ‘couper les cheveux en quatre’ (litterally, cut the hairs in four, i.e. to split hairs), which translates into Corsican language into either castrà i falchetti (litterally, to chastise the hawks) or castrà i cucchi (litterally, to chastise the cuckoos). In order to properly translate such an expression, a superintelligence must be able to:
identify ‘couper les cheveux en quatre’ as a verbal expression in a French corpus
identify castrà i falchetti as a verbal expression within a Corsican corpus
associate the two expressions as the proper translation of each other
It appears here that such an aptitude falls under the scope of AGI (Artificial general intelligence).
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 another. It seems relevant here to mention the present 8000 human languages, including some 4000 or 5000 languages which are at risk of extinction before the end of the XXIth century. It could also include relevantly some extinct languages which are somewhat well-described and meet the conditions for building rule-based translation. But arguably, this definition needs some additional criteria. What appears to be the most important is the ability to self-improve its performance. In practise, this could be done by reading or hearing texts. The superintelligent translation machine should be able to acquire new vocabulary from its readings or hearings: not only words and vocabulary, but also locutions (noun locutions, adjective locutions, adverbial locutions, verbal locutions, etc.). It should also be able to acquire new sentence structures from its readings and enrich its database of grammatical sentence structures. It should also be able to make grow its database of word meanings for ambiguous words and instantly build the associate disambiguation rules. In addition, it should be capable of detecting and implementing specific grammatical structures. It seems superintelligence will be reached when the superintelligent translation machine will be able to perform all that without any human help.
Also relevant in this discussion is the fact, previously argued, that rule-based translation is better suited to endangered langages translation than statistic-based translation. Why? Because high-scale corpora do not exist for endangered languages. From the above definition of SMT, it follows that rule-based translation is also best suited to SMT, since it massively includes endangered languages (but arguably, statistic-based MT could still be used for translating main languages one into another).
Let us speculate now on how this path to superintelligent translation will be achieved. We can mention here:
a quantitative scenario: (i) acquire, fist, an ability to translate very accurately, say, 100 languages. (ii) develop, second, the ability to self-improve (iii) extend, third, the translation ability to whole set of 8000 human languages.
alternatively, there could be a qualitative scenario: (i) acquire, first, an ability to translate somewhat accurately the 8000 languages (the accuracy could vary from language to language, especially with rare endangered languages). (ii) suggest improvements to vocabulary, locutions, sentence structures, disambiguation rules, etc. that are verified and validated by human (iii) acquire, third, the ability to self-improve by reading texts or hearing conversations.
it is worth mentioning a third alternative that would consist of an hybrid scenario, i.e. a mix of quantitative and qualitative improvements. It will be our preferred scenario.
But we should provide more details on how these steps could be achieved. To fix ideas, let us focus on the word self-improvement module: it allows the superintelligent machine translation to extend its vocabulary in any language. This could be accomplished by reading or hearing new texts in any language. When facing a new word, the superintelligent machine translation (SMT, for short) should be able to translate it instantly into the 8000 other languages and add it to its vocabulary database.
To give another example, another module would be locution self-improvement module: it allows the superintelligent machine translation to extend its locution knowledge in any language.
Also relevant to this topic is the following question: could SMT be achieved without AGI ( general AI)? We shall address this question later.
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 fix ideas) may be hard of even very hard to reach. Now a question arises: is some progress on the remaining 1% problem attainable without general-purpose AI. Prima facie, the answer is no. For it seems that progress on the remaining 1% problem requires, for example, some abilities such as being able to find the translation of a given word on external databases. For it will occur sometimes that the 1% untranslated will be due to the presence of a new word, for instance very recently created, and thus lacking in the MT internal dictionary. In order to find the relevant translated word, the machine should be able to search and find it on external databases (say, the web), just as a human would do. So, solving the remaining 1% problem requires – among other capabilities – any such ability which is part of a general-purpose AI.
Illustration from Pixabay.com
Artificial general intelligence (AGI) is prima facie a somewhat abstract notion, that needs to be refined and made more explicit. Problems encountered in implementing machine translation systems can help make this notion more accurate and concrete. The ability to find the translation of a given word on external databases is just one of the required abilities needed to solve the remaining 1% problem. So we shall mention some other abilities of the same type later.