« Video of my Talk at Digital Now | Main | On the Difference Between "Semantic" and "Semantic Web" »

May 13, 2008

Comments

Ben Toth

A couple of points in response.

1 The problem with theoretical illustrations of why a new technology is necessary is that they tend to be constructed to illustrate the benefits of the technology, and don't necessarily reflect real use cases. I once had a new search engine offered to me on the basis that it could distinguish between blind venetians and venetian blinds. We didn't buy it, but the point is that the use case was completely fanciful. Just how many real world searchers are interested in 'all products by Sony'?

2 I often have a problem with remembering the names of people in relation to a project . I have a few scraps of asociated information, some of which turn out to be wrong. So I search my e-mail, or my hard disk, and sometimes it takes a few searches. Generally I get there. The point is that I use excisting technology and it doesn't require the sort of overhead implied above.

The overall point is that the semantic and AI approaches carry a significant overhead, and the illustrations above don't justify this overhead. I am in favour of better search, and even better metadata (I am a librarian) - but better metadata driven by real use cases.

Sherman Monroe

This is an excellent piece, and important rebuttal to the discussions around Powerset/Hakia/True Knowledge, especially coming from one as yourself who is a proponent of NLP. Lately, I have been attempting to attempting to draw the distinction between what is possible and what is useful in NLP, because there is a difference. As you have observed, NLP is not a solution which provides enhancements in all cases. This is especially true in current web document search. I believe NLP will find its niche as an interface control for accessing and updating data in structured databased, such as RDF repositories, where users are averse to technical query languages. NLP will provide the user a way to use verbs, nouns, adjectives as controls and operators for expressing complex select and update queries. In this way, NLP does for the semantic web, what the GUI did for the command line.

But, again as you correctly identify, as hard as NLP is to fully realize in software, there are still aspects to information retrieval which it is not equipped to address. I believe science fiction has had a lot to do with it, but for whatever reason, people equate the ability to understand natural language as indicating human intelligence in a complete sense, when in fact, a system can be created which correctly parses the Wall Street Journal into formal logical statements, and still be unable to determine whether a particular joke is "funny". Thus a query for "funny statements made by George Bush" would still be unsolvable (if there is no explicit statement asserting that something he said was funny). The associative aspect of information is one of these very important aspects to point out. The NLP world must be prepared to 1) identify and classify the various modes of information search and retrieval, and in which of those modes can NLP add tremendous value, and 2) focus on providing additional support for user that go a step beyond the answers provided by NLP technology, including research insensitive features such as result set refinement, filtering and faceting.

Thanks so much for the insight.

Lars Ludwig

The differnece between remembering by association and remembering by keyword is similar to the difference between recognition-based search and recall-based search. The SERP offers recognition-based search after initial recall-based search. The suggest box to some degree enables recognition-based search. In my concept of 'artificial memory' I found that the personal 'association' network is the best starting point for any recall-based searching, because it encloses or points to personal recognizable concepts/things. Semantic search thus would highly benefit from personal knowledge bases.

Kingsley Idehen

Nova,

Well articulated!

My only quibble is that 15 man years away is too far out. Thus, I am hoping your unit of measure is Internet Time :-)

The Linked Data substrate is already growing organically, the injection of complimentary Lookup oriented Linked Data Spaces is also taking shape as per the UMBEL project.

For example, a corpus of Named Entity Dictionaries + Subject matter Concept schemes + Ontolology level cross mappings gives us a sustrate where "Context" attainment via Subject/Topic aided "Disambiguation" blooms. This also implies that NLP challenges of yore are much reduced.

Historically:
NLP atop SQL just wasn't/isn't feasible.
NLP over Unstructured Text (what many are grapping with today over the Web via "Semantic inside" solutions) lacks Contextual richeness, ultimately.
NLP over Structured Linked Data is a whole different ball game. Especially, when you mesh NLP with the Extraction Disambiguation prowess that Linked Data accords. This is basically what's taking shape now in the Linked Data realm.

The comments to this entry are closed.

My Photo

Twine | Nova Spivack - My Public Twine items

Radar Networks

  • twine.jpg
  • logo_v5_03b.jpg
  • logo_v5_03b.jpg

Nova's Trip to Edge of Space

  • Stepsedgestratosphere
    In 1999 I flew to the edge of space with the Russian air force, with Space Adventures. I made it to an altitude of just under 100,000 feet and flew at Mach 3 in a Mig-25 piloted by one of Russia's best test-pilots. These pics were taken by Space Adventures from similar flights to mine. I didn't take digital stills -- I got the whole flight on digital video, which was featured on the Discovery Channel.

Nova & Friends, Training For Space...

  • Img021
    In 1999 I was invited to Russia as a guest of the Russian Space Agency to participate in zero-gravity training on an Ilyushin-76 parabolic flight training aircraft. It was really fun!!!! Among other people on that adventure were Peter Diamandis (founder of the X-Prize and Zero-G Corporation), Bijal Trivedi (a good friend of mine, science journalist), and "Lord British" (creator of the Ultima games). Here are some pictures from that trip...

People I Like

  • Peter F. Drucker
    Peter F. Drucker was my grandfather. He was one of my principal teachers and inspirations all my life. My many talks with him really got me interested in organizations and society. He had one of the most impressive minds I've ever encountered. He died in 2005 at age 95. Here is what I wrote about his death. His foundation is at http://www.pfdf.org/
  • Mayer Spivack
    Mayer Spivack is my father; he's a brilliant inventor, cognitive scientist, sculptor, designer and therapist. He also builds carbon fiber trimarans in his spare time, and studies animal intelligence. He is working on several theories related to the origins of violence and ways to prevent it, new treatments for learning disabilities, and new theories of cognition. He doesn't have a Web site yet, but I'm working on him...
  • Marin Spivack
    Marin Spivack is my brother. He is the one of the only western 20th generation lineage holders of the original Chen Family Tai Chi tradition in China. He's been practicing Tai Chi for about 6 to 10 hours a day for the last 10 years and is now one of the best and most qualified Tai Chi teachers in America. He just returned from 3 years in China studying privately with a direct descendant of the original Chen family that created Tai Chi. The styles that he teaches are mainly secret and are not known or taught in the USA. One thing is for sure, this is not your grandmother's Tai Chi: This is serious combat Tai Chi -- the original, authentic Tai Chi, not the "new age" form that is taught in the USA -- it's intense, physically-demanding, fast, powerful and extremely deadly. If you are serious about Tai Chi and want to learn the authentic style and applications, the way it was meant to be, you should study with my brother. He's located in Boston these days but also travels when invited to teach master classes.
  • Louise Freedman
    Louise specializes in art-restoration. She does really big projects like The Museum of Fine Arts in Boston, The Gardner Museum and Harvard University. She's also a psychotherapist and she's married to my dad. She likes really smart parrots and she knows how to navigate a large sailboat.
  • Kris Thorisson
    Kris has been working with me for years on the design of the Radar Networks software, a new platform for the Semantic Web. He has a PhD from the MIT Media Lab. He designs intelligent humanoids and virtual realities. He is from Iceland, which makes him pretty cool.
  • Kimberly Rubin
    Kim is my girlfriend and partner, and also a producer of 11 TV movies, and now an entrepreneur in the pet industry. She is passionate about animals. She has unusual compassion and a great sense of humor.
  • Kathleen Spivack
    Kathleen Spivack is my mother. She's a poet, novelist and creative writing teacher. She was a personal student of Robert Lowell and was in the same group of poets with Silvia Plath, Elizabeth Bishop and Anne Sexton. She coaches novelists, playwrites and poets in France and the USA. She teaches privately and her students, as well as being published, have won many of the top writing prizes.
  • Josh Kirschenbaum
    Josh is a visual effects whiz, director and generalist hacker in LA. We have been pals and collaborators since the 1980's. Josh is probably going to be the next Jim Cameron. He's also a really good writer.
  • Joey Tamer
    Joey is a long-time friend and advisor. She is an expert on high-tech strategic planning.
  • Jim Wissner
    Jim is among the most talented software developers I've ever worked with. He's a prolific Java coder and an expert on XML. He's the lead engineer for Radar Networks.
  • Jerry Michalski
    I have been friends with Jerry for many years; he's been advising Radar Networks on social software technology.
  • Chris Jones
    Chris is a long-time friend and now works with me in Radar Networks, as our director of user-experience. He's a genius level product designer, GUI designer, and product manager.
  • Bram Boroson
    Bram is an astrophysicist and college pal of mine. We spend hours and hours brainstorming about cellular automata simulations of the universe. He's one of the smartest people I ever met.
  • Bari Koral
    Bari Koral is a really talented singer songwriter. We co-write songs together sometimes. She's getting some buzz these days -- she recently opened for India Arie. She worked at EarthWeb many years ago. Now she tours almost all year long and she just had a hit in Europe. Check out her video, on her site.
  • Adam Cohen
    Adam Cohen is a long-term friend; we were roommates in college. He is a really talented composer and film-scorer. He doesn't have a Web site but I like him anyway! He's in Hollywood living the dream.
Blog powered by Typepad
Member since 08/2003