Οι ιδρυτές του YahooNOTE: This is a Greek post with Semantic Web news
Image via WikipediaSemantic Hacker is a cool blog (and site) about the Semantic Web. I’ve placed them in my Web 3.0 blogroll today. They are offering an API (Application Programming Interface in geek-lingo) that can be integrated in Semantic Web applications using “Concept-Spaces”, based on weighted keywords.
However, an attempt I made to run their on-line test proved immediately and conclusively that their innovative API badly needs (Prolog-based?) Natural Language methods (NLP) of parsing and understanding human text. Without such methods, I’m afraid that the Semantic Hacker’s API… sucks! (Although this failure is occasional; most of the time the API test being quite successful). You can check this out by looking at the text I submitted to their on-line test, together with their (rather off-topic) results (copied and pasted from their test-form page):
Suppose there is an Internet Community with just one moderator; and that every person in the community keeps himself moderated: some by moderating themselves, some by obeying the (one and only) moderator. It seems reasonable to imagine that the moderator obeys the following rule: He moderates all and only those members of the community who do not moderate themselves. Under this scenario, we can ask the following question: Does the moderator moderate himself?
…/EverQuest_Games/EverQuest/Server_Specific 38…/Space_Combat/Star_Wars_Games/Star_Wars_Galaxies/Clans_and_Guilds 26Society/Philosophy/Chats_and_Forums 24Home/Family/Pregnancy/Chats_and_Forums24Arts/Literature/Authors/Blake,_William 23
1.) Moderate2.) Quarterdeck6.) Edward Grim8.) Jolly Cola9.) Welton Becket10.) Becket (film)(end of test-results copied-&-pasted from Semantic Hacker)
.
For a long time now, I have felt extremely skeptical about the claims of certain Greek… supremacists that “Greek language is the best for computing”, in the sense that it’s somehow better or more expressive, or more precise (etc.) for certain computing tasks, vaguely associated with Artificial Intelligence.
Unfortunately my knowledge of ancient Greek is limited, but my guess is that ancient Greek is a much more appropriate candidate for such claims of quality. In this post, however, I will only discuss Modern Greek, leaving ancient Greek aside (or for another posting, if there is enough time and interest).
My own opinion and experience of Modern Greek in Natural Language Programming (NLP) has been quite positive, but by no means as extreme as the ideas of some biased Greek nationalists, who persistently undervalue other languages, also believing e.g. that Bill Gates is a secret lover of Greek, and so on. According to these ignorant nationalists, writing code in today’s programming languages must be a sheer waste of time; all we need to do is simply replace them all with Greek, ending the current proliferation of computer languages using a globally revived version of ancient Greek! From my point of view, these ideas are Pure Bulshit: -There is simply no way to replace programming languages with (any) human language, no matter how perfect.
Nevertheless, if there are some advantages in Greek, from a computational linguistics’ and NLP point of view, I’d like to discuss them with you in detail, so that we can arrive at an unbiased opinion, with some positive practical results -if possible- for A.I. and computing.
There are 2 advantages of modern Greek, in NLP software, that I stumbled upon and recognised repeatedly in the past:
1) Greek spelling is heavily impregnated with additional information that can differentiate easily (and disambiguate) similar-sounding but different words. There are very few ambiguous cases (like “love” in English, which can be a verb but also a noun, or “party” -which can be either a friendly gathering or a political collectivity). This point was also discussed in another Greek blog (of my colleague j95).
2) Greek morphology is similarly full of useful surface-level characteristics, in a wide variety of easily identifiable forms (word-endings, etc) that make the automatic disambiguation of Greek grammar (as well as the detection of many aspects of unknown/new words) a lot easier than the disambiguation of English (for example); my very poor knowledge of other human languages (apart from English, Greek and some French) does not suffice to express a definite opinion as regards the possibility that certain other human languages have similar or better computational advantages (please do help, if you have some direct knowledge of relevance here).
In the last 20 years I have written a lot of Prolog code for Natural Language Understanding, as well as experimental Automatic Translation. At some point in the past I used some NLP to produce the first Greek hypertext-based dictionary software “HyperLEX” (click here for details). The task of disambiguating Greek was certainly proved considerably easier through this work, than similar efforts in English, but not as miraculously easier as some advocates of Greek Cultural Supremacism believe.
Well, your opinions and experiences are welcome! Feel free to comment (preferably) in English, but also (if you insist or can’t help it) do also comment in Greek. (If necessary, I might translate some Greek comments in English for the benefit of people who might need this, since the reverse English-to-Greek translation is unlikely to be needed).
UPDATE: A few weeks later, I was intrigued to discover more evidence that the Nationalist Pseudo-scientific myths about Greek being supposedly superior than other languages (even… computer languages) are crap; e.g. (if you can read Greek, links may be added here).
Image via WikipediaA few years ago (2003-2004) I made a detailed proposal to several Greek I.T. companies: The proposal was to “improve the performance of automatic translation software” through additional “boot-strapping code” in Prolog, which could learn from the mistakes of Automatic Translation by creating automatic generalizations in NLP (Natural Language Processing) using ILP (Inductive Logic programming).
Fed with human corrections, the proposed software would continually compare human corrections with automatic translation mistakes, so that it would learn (using A.I. techniques such as ILP) how to correct the latter, improving (the final outcome of) Automatic Translation, with time.
The human text-corrections could be stored in a so-called “Translation Memory System” (such as Trados), while the main NLP/ILP program could be a plugin or extension for already-existing Automatic Translation Software (such as SysTran).
Unfortunately, there wasn’t a single Greek I.T. company, willing to risk (my proposed salary of) 10-15 thousand euros (spread over a period of 6 to 12 months) to try out this simple and (in my humble opinion) powerful software-idea. Only one Greek company (software importers and software developers themselves) told me they might be interested, but that… they would need to see a working software demo of the idea, first! Well, I replied that the proposed initial phase of 6 to 12 months (for which I requested a decent salary) was precisely intended to cover this development phase, to arrive at an “alpha-phase software” implementing the idea. If I could support myself without their help during these few months, I wouldn’t ask for their assistance in the first place! -Instead, I would probably try to sell the “already working demo”, or start (once again in life) an I.T. company to distribute the product. But I couldn’t live without any income, during the proposed “initial phase”. Well, they immediately lost all interest in the idea, as a result; they wanted to do business with zero risks, zero investment and… zero innovation!
-Ah well, since they were a Greek company, I was not -in the least bit- surprised; always expecting the worst in Greece:
In fact, I wouldn’t even dream of implementing this innovation (in “only 6 to 12 months”) for languages I don’t understand, such as German: My idea is guaranteed to produce good results only for Greek-to-English translations (and vice-versa), which is why (to my utmost… disgust) I approached Greek companies (rather than foreign) in the first place. After a while, E-mail sent to companies all over the world was either ignored, or answered with polite replies like “no thanks, we’ re not interested in Greek at the moment”.
.
Το νέο άρθρο στο άλλο μου blog παρουσιάζει (στα αγγλικά) τον μεταγλωττιστή LPA Win-Prolog, που δέχεται ελληνικές εντολές 100% (μέσα στον ίδιο τον κώδικα), και επίσης τον μοναδικό που έχει και μουσικό MIDI interface! Όσοι πιστοί (χομπίστες, πληροφορικοί, μουσικοί) προσέλθετε, το άρθρο είναι ΕΔΩ.
Το νέο ποστ είναι κώδικας για ανάγνωση αρχείων EXCEL από SWI-Prolog.
Σε φοιτητές που μάθαιναν τη γλώσσα Prolog (αλλά δεν τη διδάσκονταν σωστά) είχα κάνει ιδιαίτερα μαθήματα πριν 2 χρόνια. Οι πρακτικές ανάγκες αυτών των μαθημάτων είχαν οδηγήσει τότε και σε βελτιώσεις ενός δικού μου μεταγλωττιστή, της GIS-Prolog (κλικ εδώ για να την κατεβάσετε).
Αν υπάρξει ενδιαφέρον, τα ιδιαίτερα μαθήματα PROLOG θα ξαναγίνουν φέτος (e-mail στο omadeon@hotmail.com αν ενδιαφέρεστε).
Related articles
.
Today, at 3am Greek time, WordPress statistics for visitors in this blog indicated a remarkable rise in popularity, more than 6 times the usual average. Detailed analysis shows 590 clicks in only one day: (περισσότερα…)
Image by NJ – Library Events via FlickrMany thanks to readers who appreciated this article (more than a thousand, so far). However, please note as…
A few days ago, I wrote a short posting in this blog about the fact that The ultimate high productivity programming language is PROLOG. A few days later, I was quite astonished to see that this posting became extremely popular! It was listed as no. 35 in the “most popular postings worldwide” list of WordPress a few days ago. (You can click here to verify this claim, scrolling down to no. 35). Meanwhile, some people discussed the Prolog posting elsewhere on the Web. E.g. a discussion in the wiki-site “reddicious”, as well as in another blog (“The Hungry Brain” – here).
As a result, I will continue to write about Prolog, about why I use it, about the wonderful things you can do in it, and (last but not least) about the fallacy that it cannot be used as a “general purpose programming language“. Well, of course it can be used as a “general purpose language”! This is the philosophy of Visual Prolog -for example- created by an innovative bunch of nice people in Denmark (whom I met personally in a Prolog conference, in April 2006). They created this Prolog dialect and designed it for maximum speed, highest efficiency and ease of use, with a Visual development environment and an object-oriented structure (in the latest versions, 6 and 7). (more about this later, in another posting)
However, today I want to talk about one aspect of Prolog (and many similar Logic Programming languages, e.g. Mercury) that is rarely discussed and very rarely appreciated: The fact that… (περισσότερα…)
Image via WikipediaActually, It is the combination of PROLOG with high-speed enhancements in Pure Assembly language, which I pursue -and recommend- as the best possible methodology for Data Mining and A.I. applied to HUGE DATA (which is the typical situation in our time). (περισσότερα…)
English summary (update): This Greek post tells the story of “HyperLOGIC R&D“, a small Greek company that produced (in 1991) the first HyperText-based intelligent dictionary software in the world (with embedded speech), a program called “HyperLEX” (discontinued in 1998). It was developed in Prolog and pure Assembly language. Although an MS-DOS program, it had a lightning-fast Graphic Environment, with multiple mouse-controlled resizable windows, a special editor-window (for source- and target- texts in translation) and intelligent Morphological / Spell-checking capabilities, etc. Initially, I started “HyperLOGIC R&D” aiming to achieve a “horizontal structure” company with many creative profit-sharing participants. However, this vision of “collective business activity” was not fully implemented, due to various practical difficulties (in Greece).
Posted by 
omadeon
Η επόμενη σκαναρισμένη εικόνα είναι μία σελίδα του προγράμματος (φυλλαδίου) παρουσίασης καινοτομιών προϊόντων μιας Κοινοτικής έκθεσης στο Ζάππειο, το Μάρτιο του 1993, με τίτλο “Γλωσσομάθεια και Ευρωπαϊκός Πολιτισμός”: (περισσότερα…)
Omadeon
Ο Αιρετικός
dennisvtheterrible
That Crazed Alien penguin
KnowDame
Ζώης Σταθερός
Ολογιστής
lchronop
Πρόσφατα σχόλια