Saturday, February 24, 2007

"Text Enrichment" to Improve Written English

An interesting application of NLP compares user-generated input against a vast database of known proper English to generate suggested improvements to help readability and fluency.

By using a corpus filled with millions of real-world modern English texts, the software is capable of recommending thousands of grammatical corrections, as well as relevant adjectives, adverbs and synonyms. The Israel-based company WhiteSmoke hopes to help improve emails and documents by leaping well ahead of the limited grammar checking functions found in programs like Microsoft Word.

Sunday, February 18, 2007

Autonomous Cars by 2030.

Only 23 more years until we can sleep while driving to work. That's the prediction of scientists working on this year's DARPA Urban Challenge, the third annual Grand Challenge featuring a 60-mile course for driverless vehicles through a simulated city.

The Stanford researcher also predicts battlefield use of this technology by 2015--conveniently just in time to meet the Congressional deadline to make a third of all military vehicles autonomous. So not only will the technology drastically reduce drunk driving accidents, it will hopefully reduce deaths by roadside bomb as well.

Saturday, February 17, 2007

PARC to build NLP Search Engine

The Palo Alto Research Center (of Xerox fame) has licensed its sophisticated natural language processing technology to a start-up hoping to develop an NLP-powered search engine.

The start-up, called Powerset, intends to create a system where users search for data by entering plain-language queries, rather than using keywords. Similar efforts have been launched by MIT and others to solve the problems of automated response generation. With decades of research and significant resources behind them, Powerset hopes to foster the third generation of search engines, following in the footsteps of AltaVista and Google.

Monday, February 12, 2007

Boeing Brings the Magic

Major defense contractor Boeing displayed several very impressive advanced technologies at the annual Airlift/Tanker Association convention in Orlando last fall...

Following on the (eventual) success of the V-22 Osprey tiltrotor aircraft, Boeing is currently developing a quad-tiltrotor design--that is, a VTOL aircraft with four rotating turboprop engines that convert from helicopter to airplane mode. The Boeing QuadTiltRotor was recently awarded a contract for the US military's Joint Heavy Airlift study. Replace those turboprops with turbofans and we're getting close to the flying "Hunter-Killer" design from T2...

Perhaps the most impressive technology showcased by Boeing was its work in pulse jet lift thrusters. This system groups together a number of very small, simple & highly efficient pulse jet engines to provide powerful, controllable & fault-tolerant VTOL ability. Boeing claims to have overcome the poor fuel economy issues that have plagued pulse jets since their first principal use in the V-1 rocket. Future applications include the Light Aerial Multi-purpose Vehicle (LAMV) concept, in which a (patented) pulsejet ejector thrust augmentor provides VTOL capability, while traditional jet engines allow for standard flight like an ordinary fixed-wing aircraft. Scale it down a bit, and perhaps we'll all be riding hoverboards someday...

Not shown at the A/TA Convention but prominent on the Boeing Integrated Defense Systems website is the A160 Hummingbird helicopter UAV. The Hummingbird's first test flight was in 2002 and is currently in development under contract with DARPA.

Saturday, February 3, 2007

Human-like Decision Making in Software

For those employees who believe they cannot be replaced with a very small shell script, your days may be numbered.

Compsim LLC, a seemingly small company based outside of Milwaukee, has developed a patented system which they claim can add human-like decision making to software applications, devices or even websites. By using Knowledge Enhanced Electronic Logic (KEEL) Technology to design custom decision processes, Compsim's customers can build expert system software capable of making judgmental decisions.

Like any expert system, KEEL is a knowledge-based system that uses domain-specific information provided by human experts to generate decisions based on various inputs. However, KEEL is different because it allows for graphical development of decision formulas or "policies" in a web (as opposed to tree) structure, and its solutions are fully explainable and auditable. The company's website has a variety of interactive demos, including UAV guidance & collision-avoidance and automatic dispensing of drugs. Compsim forsees numerous applications for KEEL technology, from automotive & medical diagnostics, to industrial automation, to stock market forcasting, to intelligent weapon systems.

The next step for this line of research is to incorporate machine learning into the development of decision policies. Compsim admits that while KEEL systems can be designed to adapt, they are not "true" learning systems in that they are unable to independently integrate new information sources. An expert system that can learn could potentially become an "expert" on anything, and might be a path towards artificial general intelligence.