Comments on: Playing With Wolfram Alpha

By: Wolfram Alpha Answers Its Own Questions… | Search Done Right

Wolfram Alpha Answers Its Own Questions… | Search Done Right — Mon, 01 Mar 2010 03:25:26 +0000

[...] answer a small portion of the questions asked of it. A lot has been said about its limitations in NLP but I actually see WA’s limitation more related to the data – how it collects it and how it [...]

By: Wolfram Alpha - Re-Inventing the Command Line - Things On Top

Wolfram Alpha - Re-Inventing the Command Line - Things On Top — Fri, 12 Jun 2009 07:00:05 +0000

[...] overnight, especially since we’re already so accustomed to the quick and dirty web search. Wolfram Alpha can be both tedious and puzzling to interact with, and must therefore provide some serious extra value if it expects us to make the [...]

By: Daniel Tunkelang

Daniel Tunkelang — Wed, 13 May 2009 01:19:03 +0000

Indeed, I’d love it if the response to my query helped me learn how to better structure future queries to avoid the travails of trial and error. And, of course, I’d appreciate a documented user guide / API.

By: Christopher

Christopher — Tue, 12 May 2009 02:41:32 +0000

Using a structured query with selective natural language support (synonyms for subjects, operators & predicates) they could do something like this for the above query.

COMPARE REVENUE of Microsoft, Yahoo & Google by NUMBER of EMPLOYEES.

By: Daniel Tunkelang

Daniel Tunkelang — Mon, 11 May 2009 19:36:09 +0000

In the next week, according to the New York Times.

By: Diamonds

Diamonds — Mon, 11 May 2009 18:02:23 +0000

Looks very interesting, when do they intent to release this?

By: Daniel Tunkelang

Daniel Tunkelang — Fri, 08 May 2009 20:13:40 +0000

Nate, great to see you at The Noisy Channel! I agree that they should be thinking this way; but they really seem to be pushing the NLP angle. And I haven’t heard a peep about plans for an API. From this distance, it feels a like a science project that needs some adult supervision.

Anyway, to your queries:

Koala has two associated result pages: the species (default), which shows the complete taxonomy of Phascolarctos cinerius, and see-also to for the dictionary / thesaurus entry.

Titanic offers a “coming soon” for the disaster event (default), and see-alsos to an IMDB-like entry for the movie and a dictionary / thesaurus entry.

No luck with my vanity query. Some people are in their database, but I’m clearly not famous enough.

By: Nate Treloar

Nate Treloar — Fri, 08 May 2009 20:01:46 +0000

I’d be surprised if the Wolfram folks are not thinking in terms of a platform with the APIs and programmatic access, as opposed to just a destination for casual users. That would be the ‘wikinomical’ thing to do.

Daniel, what does Wolfram do with queries like “koala”, “titanic”, or “daniel tunkelang”?

By: Daniel Tunkelang

Daniel Tunkelang — Fri, 08 May 2009 19:11:12 +0000

I hope they have the sense to deliver the programmatic access that researchers and marketers need. They seem to be torn between two incompatible directions. On one hand, their computational focus could really appeal to information professionals. On the other hand, their NLP interface seems aimed (misguidedly, in my view) at casual web searchers. I hope they go in a direction that plays to their strengths, and that they can package it up to be useful to folks would would appreciate a computational engine. But their lack of clarity of purpose thus far is a bit discouraging.

By: Perry Hewitt

Perry Hewitt — Fri, 08 May 2009 13:43:42 +0000

This is fascinating stuff — agreed on the programmatic access. I know researchers who would love to use this with census information. And marketers, should a tool like this fall into their evil hands, might like it to talk to their dbs …

By: Daniel Tunkelang

Daniel Tunkelang — Fri, 08 May 2009 12:46:19 +0000

Remaseshan: no luck–and not surprising, as they specialize in objective data. They’d have to quantify “lead”. Plus I doubt their curated data has anywhere near the completeness to include impact factors for HCIR researchers!

Max: Endeca is privately held, so we’re not in any of the databases they use. I know–but if I told you, I’d have to kill you. Bad for my readership numbers!

By: Max L. Wilson

Max L. Wilson — Fri, 08 May 2009 07:43:43 +0000

Ramaseshan’s sounds good. I was pleasently surprised last time i searched google for ‘Improving search interfaces‘

have you also tried adding (Endeca revenue/endeca employees)? for interest’s sake.

By: Ramaseshan

Ramaseshan — Fri, 08 May 2009 04:53:10 +0000

Is it possible find results for queries such as “who is the lead researcher in faceted browsing”?

By: jeremy

jeremy — Fri, 08 May 2009 04:47:13 +0000

I suddenly feel like I should be relearning Prolog…

By: Daniel Tunkelang

Daniel Tunkelang — Fri, 08 May 2009 03:22:05 +0000

Joe: no luck on the time series–I can only get that for simple queries like “microsoft revenue 1998-2008″.

Anand: I can get “united states car accidents” and “united states population density”, but no correlation–or even a break down of either statistic by state.

Gene: I agree, this screams for programmatic access.

By: Gene Golovchinsky

Gene Golovchinsky — Fri, 08 May 2009 01:01:19 +0000

Seems like a good application for YQL to make it easier to mash up the data and to treat them uniformly in a programmatic way.

By: Rangachari Anand

Rangachari Anand — Thu, 07 May 2009 22:29:31 +0000

Looks interesting. Try car accidents in the US correlated with population density.

By: Joe Mako

Joe Mako — Thu, 07 May 2009 21:38:27 +0000

That looks great for the current year. How would the query need to be structured to see a line graph of those 3 numbers by year for the last 10 years?