Machine Analysis of Scientific Papers

There's a lot of exciting work going on in NLP right now, and it's hard to keep up...and even harder to maintain a blog about all of it! Larry pointed me to an article from last year detailing an automated tool for analyzing and comparing experimental reports.

This project sounds like some sort of XML markup scheme for outlining scientific papers, similar to the ontologies powering the semantic web initiative. It probably involves too much overhead to be widely adopted and therefore be useful, as it likely requires the author to spend an awful lot of additional time constructing papers such that the EXPO system could parse it. A much more elegant method would be for the system to perform an automatic analysis and markup of the text, however that would require NLP technology beyond what's currently available.

As you might imagine, a similar hurdle exists for the adoption of the semantic web in general. However, the analysis & synthesis of peer-reviewed journals presents us with yet another "killer app" for NLP. There is simply far too much information covering any given topic being generated for a human being to digest, even experts in a particular field...let alone a renaissance man or polymath to synthesize from diverse fields. Only a machine with advanced NLP capabilities would be able to make sense of it all and create new knowledge from what's already available.

Commercially Available Automatic Summarization Software

In his weekly article, Robert X. Cringley profiles a company that has created software which is seemingly able to create relevant summaries of arbitrary size from bodies of text covering all possible subject domains. This is precisely the sort of thing I wanted to accomplish with my AutoSummary project. Automatic summarization is yet another application of NLP as a solution to the problem of too much information for humans to deal with. Learn more about iReader at Syntactica.

Marvin Minsky AI Podcast from 2001

Slashdot points us to three podcasts from MIT Professor Marvin Minsky where he discusses the past failures of AI and the hope for progress in the future. Part One can be found here.

"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.

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.

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.

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.