How to build your own "Watson Jr." in your basement
1–10 of 29 posts
Re: How to build your own "Watson Jr." in your basement
#2I somehow cannot give up daydreaming wistfully about a personal CM-5. From a previous discussion on HN it seems it still is going to be an expensive thing to build as a toy project. Particularly because of the hyper-cube inter-connection. Not sure if the source code for star-Lisp is available. But I think an emulator lives on at Sourceforge.
Edit 1: Here it is http://sourceforge.net/projects/starsim/
Edit 2: Just doubled checked, the Sourceforge repository has no code !! But I found it here http://examples.franz.com/category/Application/ParallelProgr... @dhess Thanks a lot for that link. I just ordered a copy :)
Re: How to build your own "Watson Jr." in your basement
#3I somehow cannot give up daydreaming wistfully about a personal CM-5. From a previous discussion on HN it seems it still is going to be an expensive thing to build as a toy project. Particularly because of the hyper-cube inter-connection. Not sure if the source code for star-Lisp is available. But I think an emulator lives on at Sourceforge. Edit 1: Here it is http://sourceforge.net/projects/starsim/ Edit 2: Just dou…
I think you might like this book: The Paralation Model, by Gary W. Sabot.
http://www.amazon.com/Paralation-Model-Architecture-Independ...
Re: How to build your own "Watson Jr." in your basement
#4Watson has become an unbelievable marketing tool for IBM.
Re: How to build your own "Watson Jr." in your basement
#5My hunch is that 90-99% of all Jeopardy questions can be answered with information in Wikipedia/Wiktionary, properly understood.
So I'd start with Wikipedia: ~30GB uncompressed full article text. Break it into chunks; canonicalize phrasings to be more declarative, and include synonyms/hypernym/hyponym phrasings (via something like WordNet), so that various 'cluesy' ways of saying things still bring up the same candidate answers.
Because it's free and compact and well-structured, throw in Freebase, too.
Jeopardy goes back to certain topics/answers again and again. So I'd scrape the full 200K+ clue "J!Archive", and use it as both source and testing material (though of course not testing the system on rounds in its memory).
And I'd add special interpretation rules for commonly-recurring category types: X-letter words, before-and-after, quasi-multiple-choice, words-in-quotes.
I think such a system might get half or more of the questions in a typical round correct, and in a matter of seconds, even on a single machine.
Re: How to build your own "Watson Jr." in your basement
#6Watson has become an unbelievable marketing tool for IBM.
Has become? From the beginning, Watson's purpose has been to advertise IBM's computers.
Re: How to build your own "Watson Jr." in your basement
#7My hunch is that 90-99% of all Jeopardy questions can be answered with information in Wikipedia/Wiktionary, properly understood. So I'd start with Wikipedia: ~30GB uncompressed full article text. Break it into chunks; canonicalize phrasings to be more declarative, and include synonyms/hypernym/hyponym phrasings (via something like WordNet), so that various 'cluesy' ways of saying things still bring up the same candid…
"properly understood" is the whole point. That's the hard problem they are trying to solve.
Re: How to build your own "Watson Jr." in your basement
#8Search optimization: No, this team focused on making IBM Watson optimized to answer in 3 seconds or less. We can accept a slower response, so we can skip this.
That makes me laugh. I'd guess that search optimization effort has a power law response here. 3 seconds is extraordinary, 1 minute is tricky, 10 minutes is possible after some solid effort, 3 days-heat death of universe is what you get without optimization.
Not saying you actually ignore it. It's built into those libraries they casually throw around. Just thought the wording was funny.
Re: How to build your own "Watson Jr." in your basement
#9My hunch is that 90-99% of all Jeopardy questions can be answered with information in Wikipedia/Wiktionary, properly understood. So I'd start with Wikipedia: ~30GB uncompressed full article text. Break it into chunks; canonicalize phrasings to be more declarative, and include synonyms/hypernym/hyponym phrasings (via something like WordNet), so that various 'cluesy' ways of saying things still bring up the same candid…
I'm not certain, but I'd bet Watson was explicitly not allowed to use something like J!Archive as training data. For one, the questions used in the Jeopardy games it played were drawn randomly from previous questions. More importantly, though, learning a stilted, domain specific language model to play Jeopardy isn't anywhere near as challenging, impressive, or worth pursuing than generating something that includes Jeopardy as a subset of its capacity.
Now Watson was tuned on Jeopardy questions. I'm sure the learning processes were adjusted in light of mistakes made on the Jeopardy corpus, but interpolation is far less big a deal than a full language model.