Tag Archives: natural language

Gatfol Language Semantics Announces First Integrated Prototype Installation

Gatfol is a South African origin provisionally patented (USA) Search Technology with built-in human language intelligence

Centurion, South Africa (PRWEB) April 26, 2013

Gatfol serves base technology to provide digital devices with the ability to process human natural language efficiently.

The goal of truly semantic search has not yet fully been realized. The main problem is the enormity of ambiguous word permutations of semantic equivalence in even the simplest of phrases, which up to now has processing-wise required huge structured lexicons and ontologies as guides.

Gatfol is developing its patented technology commercially to massively improve all keyword-based search in the millions of in-house and public online databases worldwide. A first fully integrated prototype has now been installed on a clustered network of twenty seven desktop computers in Centurion South Africa.

Founder and CEO Carl Greyling firmly believes that Gatfol technology is crucially needed by many digital processors worldwide. Without a Gatfol-type solution, further development in many large digital industries is difficult. These include: Online retail (Amazon, Staples, Apple, Walmart), online classified advertising (Craigslist, Junk Mail), online targeted advertising (Google, Facebook, Twitter, Yahoo), augmented reality (Google Glass), national security in-stream data scanning (FBI, CIA, most governments worldwide), abuse language filtering in especially child friendly online environments (Habbo Hotel, Woozworld), image- and video auto-tagging for security monitoring (most police forces worldwide), human-to-machine natural language interfaces (all web search engines like Google, Yahoo!, Bing, Ask) and web text simplification for disadvantaged web users.

The Gatfol operational technology comprises multiple redundant local machine-based master and slave software nodes to process input in parallel to ensure extremely high throughput speeds at very large input volumes, regardless of machine- and CPU hardware configurations. This applies to the full production cycle from web RSS-based sourcing to microsecond delivery of output to calling applications. Processing speed increases are proportional to the volume of nodes applied.

Unlike almost all competing technology available today, Gatfol provides robust parallel processing power from even simple desktops or laptops. With all data streams staying local to the processing machine, application of Gatfol technology in especially security-based environments (ie battlefield deployments) is not compromised by networking- and online processing- or data transfer exposure.

With a simulated Hadoop multiple master-and-slave node architecture built around simple but robust Windows™ executable files and with multiple fall back redundancies around both master and slave functions, as well as all nodes individually carrying full word relationship databases, reliability of throughput is ensured – especially critical in large volume streaming functionality.

With a base in ordinary executable files, Gatfol also secures legacy hardware and OS (Windows XP and older) functionality and easy portability in instances of local machine OS upgrades.

The Gatfol standalone footprint can be easily incorporated into wider distributed processing architecture including full Hadoop-, as well as cloud based environments – with corresponding scalability in throughput performance.

RSS sourcing is widely scalable. Throughput has already been successfully tested at nine terabyte of web text per month.

Current best input-output performance of a 50-100 level deep Gatfol semantic crystallization stack on a standalone desktop (Intel Dual 2.93 GHZ 3.21GB RAM Windows XP) for text throughput is 3.6mb/hour for a single Gatfol cluster instance, 11.78mb/hour for a 10-cluster instance and 98mb/hour for a 100-cluster instance.

On a standalone desktop (Intel Quad 3.30 GHZ 2.91GB RAM Windows XP) best text throughput for a 50-100 level stack on a Gatfol 1000-cluster instance is 611mb/hour.

Total text throughput for a 50-100 level stack on an ordinary desktop Microsoft Networks-linked grouping of 20 desktops (Intel Single core 2.8GHZ 768MB RAM Windows XP) each running a Gatfol 100-cluster instance is 1.9GB/hour – giving maximum text output volume of 140GB/hour.

About Gatfol

Gatfol is the culmination of 12 years of work originating in the UK. Virtual auditing agents were developed using an intelligent natural language accounting system with neuro-physiological programmatic bases to penetrate, roam in- and report on patterns in financial data. This led to an EMDA Innovation in Software award from the European Union in 2006 and formed the basis of the Gatfol algorithms and technology currently in development.

Gatfol’s immediate aims are to improve search using semantic intelligence (meaning in data), both on the Web and in proprietary databases. Gatfol technology was provisionally patented in the USA in April 2011 and has PCT protection in 144 countries worldwide.

It is Gatfol’s vision to eventually enable humans to talk to data on all relevant interface devices.

Those interested in learning more about Gatfol technology can visit Gatfol Blog. For more information, contact Carl Greyling at Gatfol on +27 82 590 2993.

The Solution: Gatfol Web Text Simplification and Search Augmentation…


Gatfol is a provisionally patented, natural language, browser-based mobile technology that opens up the web to challenged readers in Africa and emerging economies worldwide. Gatfol technology simplifies web text instantly to match the preferred reading level of any language challenged (semi-literate) web user.

The Gatfol technology traversed a 9-year development period before patent application. This solid ground level base enables Gatfol to efficiently “translate” even large volumes of web text very quickly into simple reading components. The technology is unique in that it provides for a fast multiword-to-multiword stepwise crystallization of natural language (English) from semantic complexity to semantic simplicity and vice versa.

Gatfol also instantly translates search engine queries (i.e. Google) typed in simple language by reading-challenged users, into sophisticated web language to enable real-world keyword matching – even for complicated topics in technically advanced industries :

Gatfol has operational code frameworks available to run as a Cloud-based service or in case of confidential data streams – as a local master and slave technology to quickly simplify web language – even in-line and in real time. This confidential data stream technology can run on as simple a platform as a single desktop machine or ordinary Windows network set-up.

As an adult further education language tool, Gatfol is very cost effective. Most of the large African literacy programs carry a cost per semi-literate learner per year of around $50. Gatfol web text simplification technology brings down the costs per semi-literate learner substantially. Gatfol calculates that for just $1.80 per year, the English vocabulary of a challenged reader can be increased a HUNDRED fold – from a vocabulary of 200 words to a vocabulary of 20 000 words.

Web-enabled mobile devices using Gatfol technology also give disadvantaged users an opportunity to “see” online web language of a higher semantic complexity than by using the relatively basic English language material covered by further education programs.

Gatfol is words…words are power…

Gatfol and the Programming Language of the Future…

What we really want is to squeeze the amazing richness and complexity of the
real world into the confining structure of an ideal future programming environment.


With Gatfol.

Gatfol is the core technology platform to transform real world concepts through SIFT
matrixes automatically without any human involvement into any possible semantic equivalents.
Gatfol algorithms perform the role of  “intelligent human interpreter” between programmers and hardware.

With Gatfol, programming in 2020 will be nothing different
from the language used by Aunt Lavinia and Aunt Showie over tea….

Can a Machine Rewrite Shakespeare?

Even with mankind firmly in the 21st century and more than four decades after HAL from Space Odyssey 2001 showed humans the way to go, it seems unfathomable that the everyday ability to converse with machine information in natural language is not a reality after all these years.

Wouldn’t it be amazing if we could get computers for instance to read Shakespeare’s plays and perhaps re-write them using different words – and not just by applying synonym replacements or related concepts?  Imagine even a machine giving us a completely “new” play in Shakespeare’s writing style? Just think of the impact that reaching this technological level would have on a rapidly exploding data world that hungers for increased semantic intelligence filtering capabilities.

Why are we not there yet?

What hasn’t been done and what represents the “holy grail” in semantic analysis on a technical level, is an efficient multi-word to multi-word grammar and semantic transformation in text input-output flow.

Current semantic (meaning in language data) technologies available are crippled by a serious flaw. It is difficult to generate a semantically and grammatically equivalent body of text from an existing repository of language patterns and word combinations. Additionally, sentence structure and logical meaning flow have to fit in with the physical and rational make-up of the world we live in.

The flaw comes in when we literally have to “show computers our world”.  By attempting to “categorise” words or concepts beyond the English left-right, Arabic right-left, or Chinese up-down reading and writing order, most of the modern semantic intelligence technologies delivers a level of complexity that is unsustainable in terms of permutations.

By laying down logical concept rules, such as “a dog is alive” and “things that are alive replicates” giving us “a dog replicates”, current technologies hope to be able to create systems that generate and perpetuate rules of logic – and eventually represent some type of “machine intelligence” on a level with human thinking.

Categorisation systems very quickly run into the “permutation problem”: imagine any sentence of about 8-10 words, i.e. “I really appreciate my mother in the morning”. What would happen if we replace let’s say each word with 10 equivalent words that fit both grammatically and semantically? i.e. “I definitely/positively/demonstratively…” “like/admire/love my mother…”. Taking the original word phrase and randomly inserting the replacement words in all possible groupings that still make sense, we get 100 million phrases that are ALL grammatically and semantically equivalent – and we are only still saying that we feel positive about our mother some time early in the day!

Even the smallest body of text of even minimum complexity, obviously has trillions upon trillions upon trillions of grammar-semantic equivalents. In the usage of these logical categorisation systems, we just do not have the concept-combination multiplication power to cover the permutation problem. World-wide effort since the 1980’s around ontological classifications, hierarchical categorisation, entity collections and logic rule based systems have therefore not succeeded quite as envisaged. We can think of CYC, OpenCYC, Mindpixels and Wordnet amongst many.

“Permutations” is the villain that everyone hopes will disappear with “just a few more categorisations…”

Alas, it will not.

What is needed is a small compact “semantic engine” that can “see” our world and that will enable trillions of concept permutations to adequately represent the resulting image.

With an abundance of data in a complex and highly unstructured web and without a powerful enough “engine”, we really don’t have much chance of ordering and classifying this data such that all concepts inside of it relates to everything else in a manner that resembles our real human world holistically.

The search is therefore on for a technology that could take a quantum leap into the future. If we can start by enabling machines to “rewrite Shakespeare”, we should be able to develop an innovative, ontology-free, massively scalable, algorithm technology that requires no human intervention and that could act as librarian between humans and data.

The day when humans are able to easily talk-to, reason and “casually converse” with unstructured data will lead to a giant leap in the human-machine symbiosis and – after far too long a wait – in our lifetime we can perhaps still experience a true Turing “awakening”.

 To see a version of Shakespeare’s Hamlet re-written by a machine, have a look at…