So what’s been happening with Wolfram|Alpha this summer? A lot!
At a first glance, the website looks pretty much as it did when it first launched—with the straightforward input field. But inside that simple exterior an incredible amount has happened. Our development organization has been buzzing with activity all summer. In fact, it’s clear from the metrics that the intensity is steadily rising, with things being added at an ever-increasing rate.
Wolfram|Alpha was always planned to be a very long-term project, and paced accordingly. We pushed very hard to get it launched before the summer so that we could spend the “quiet time” of our first summer steadily enhancing it, before more people start using it more intently in the fall.
Two really great things have happened as a result of actually getting Wolfram|Alpha launched. The first is that we’ve discovered that there’s a huge community of people out there who want to help the mission of Wolfram|Alpha. And we’re steadily ramping up our mechanisms for those people to contribute to the project.
The second thing is that we’ve now got actual examples of what people want to do with Wolfram|Alpha—hundreds of millions of them. And it’s terrific to see that so many of them work so nicely. But for us now the most valuable thing is seeing what doesn’t work yet. Because that shows us what we need to add to Wolfram|Alpha.
There are several components. One is knowledge domains. Things people want that Wolfram|Alpha doesn’t yet know. The good news is that there’s been very little that’s come through that wasn’t already somewhere on our to-do lists. They’re long lists. But we can now be confident that they’re good lists.
A second big component is linguistics. Close to half the time that Wolfram|Alpha doesn’t give a result, it’s not because it doesn’t have the necessary knowledge, or can’t do the necessary computation. It’s because it doesn’t understand what’s being asked.
It’s very interesting to see the kinds of queries that come into Wolfram|Alpha, and how they’re phrased. We’re really seeing a new human language. Based on ordinary language, but without a lot of its niceties. Probably closer to the way people think internally.
Wolfram|Alpha is a bit like a child: it’s being exposed to a new language, and it’s got to learn from examples how to understand it. The good news, though, is that Wolfram|Alpha is getting a lot of examples. Already a couple of orders of magnitude more than a child ever gets.
One of our big activities this summer has been inventing new techniques to take advantage of all this. It’s very interesting science. Much of it based on NKS. We’ve made some great advances, which we’re steadily implementing in the Wolfram|Alpha system.
The results so far are quite encouraging. In just a couple of months, we’ve reduced the “fall-through rate” of queries we don’t understand by 10%. And this is just the beginning. The techniques we’ve invented can clearly go a lot further. And we have all sorts of ideas for completely new techniques.
One of the fascinating things for me about the Wolfram|Alpha project is the way it mixes deep theoretical ideas with very practical implementation.
And one of the great achievements this summer has been streamlining the implementation. New data comes into Wolfram|Alpha all the time. But we had a plan that once a week we would update the underlying code of Wolfram|Alpha.
Some people in our development team thought this was impossible. But working on Mathematica for the past 20+ years, we’ve come up with some pretty good software engineering techniques—particularly making use of Mathematica itself to do system building, testing, and deployment.
Well, I’m happy to report that we have indeed managed to make the idea of one code update per week for Wolfram|Alpha work. In fact, it’s been working every week for the past 13 weeks!
So what’s been in all those updates?
I should explain that through the course of the summer we’ve been steadily expanding the Wolfram|Alpha development team, adding a lot of very talented people from around the world.
But in writing this blog post, I just looked up what’s actually happened to the Wolfram|Alpha codebase since launch. And I have to say that I’m quite astonished: it’s grown by a staggering 52%—adding well over 2 million lines of Mathematica code.
There have also been nearly 50,000 manual groups of changes to our data repositories over the past 3 months.
It’s hard to have a good metric for how many completely new knowledge domains we’ve added. But based on new source files, and new underlying databases, I think it’s been between 10% and 15%. (There’ll be other blog posts talking about the specifics—though we tend to be a bit bashful about new domains when they’re first added; they usually take a little while to reach maturity, and by then they don’t seem as new to us.)
One of the most difficult things about keeping our weekly update schedule is getting testing done.
We test Wolfram|Alpha at many levels. Its data, both static and real-time. Its underlying computation. Its linguistic processing. Its presentation layer. And its web operation.
Continually through each day we’re building new versions of the Wolfram|Alpha system, and doing automated tests. Over the course of the summer, we’ve dramatically increased the number and types of tests we have, both custom-built and derived from actual query streams.
Of course these tests find bugs, which we’re continually fixing. (Each week, Monday and Tuesday are bug-fixing days for all our developers.)
But what’s really great is how many users of Wolfram|Alpha send in helpful bug reports and suggestions. In fact, it’s been a big effort just to keep up with all of them.
As of now, of all the feedbacks we’ve received, we’ve classified 54,233 of them as bugs or suggestions. Of these, 31,006 are now in our implementation queue, boiled down to about 5800 to-do items.
At the beginning of the summer, we were taking care of about 250 to-do items from all sources per week. Now it’s up to nearly 600 per week.
And so far we’ve been able to tell 3907 people that the bugs they reported have been fixed.
It’s really very exciting watching Wolfram|Alpha develop. Every day there are zillions of little changes and fixes that get made (”add an extra name for a type of spider”; “fix the timezone for an outlying settlement”; etc.), while major new domains and frameworks are getting built up.
There’s also infrastructure development. Making Wolfram|Alpha run well on more web browsers. Optimizing performance. People may have noticed recently that there are no longer URLs like www12.wolframalpha.com; it’s always just www.wolframalpha.com. That seemingly minor change reflects a large engineering effort to optimize load balancing between our colocation facilities.
In addition to new content, we’ve been working very hard on new delivery and interface mechanisms for Wolfram|Alpha, which we expect to be able to announce quite soon.
It’s been a great first summer for Wolfram|Alpha. It was a mad dash to launch Wolfram|Alpha when we did. But we’ve actually built up over the summer to an even greater development intensity, though now with a progressively larger team and increasingly streamlined development systems.
These are exciting times. The vision of Wolfram|Alpha is really working! With every day bringing new advances. Progressively building up the largest coherent repository of human knowledge ever assembled.
Which we’re now getting ready for its “fall traffic”…
ANY METHOD TO DETERMINE A CURVED LINE’S EQUATION?–(PLACED ON A CARTESIAN GRAPH IN I QUADRANT EG.)—THANKS
Hi,
Based on my teaching experience at the undergraduate level, there seems to be no connection between the questions students ask, and the answers a teacher or software might provide. This is because, in order to solve a problem, students must first extract keywords from the question, and connect these with the keywords they ingested while doing homework. Only then will they be able to find out what “kind” of problem they’re having. Once this is done, students are able to ask questions which can be answered. But not before. The missing element here is: keyword acquisition/recognition.
Perhaps my comment of 30 August @ 6:56 PM will provide another perspective on solving the problem you describe.
I’d like to see a switch put in so that when you search the web you can tell it to exclude or include commercial sites or personal web sites. It seems to me that the web has gone from being a large collection of personal web sites to an even larger collection of commercial web sites who unfortunately can pay to have their sites listed frst in a search. The personal web sites can be buried so far down that one never finds them. It would be a great way for people to connect if when searching you could say exclude commercial web sites; then only personal web sites would come up in a search.
Very interesting - I am a fan of Wolfram Alpha although many of the commonly used styles of query which doesn’t work even when adding = or + or and/or. A deeper exploration of the linguistics should make a fascinating and hopefully productive.
Well done Wolfram|Alpha team.
while we were thinking that existing search engines have already offered what is feasible, you came and offered us something we never thought we could get. it s amazing. with the steps that you are taking it is going to be more and more interesting as you have set in your vision on a unexplored landscape.
i have been impressed with your product and iam eagerly awaiting to see your organisation’s exponential growth.
You need a concise statement of about 3 sentences explaining What the product/service is. You speak of a vision and mission but it isn’t articulated in the updates. Basic communication.
Love WolframAlfha so far, despite necessity to learn new way of doing queries - i fail on more than 80 % of those that I try to enter intuitively/logically… so far it’s a bit too mathematic and not user friendly, but i’m sure it’s a matter of product development or user learning, idea is still genius
I experience the same frustration. I cannot figure out how to best ask a question. I have yet to receive any full or directed answer to a query. Please explain HOW to successfully frame the question.
If this information is located elsewhere, it would be useful to put that link near the question box.
Thx
Thank you very much for the info. Looking forward to the greatness of the site.
It you be a good idea if engine returns the references of the website(s) where it extracted the information from. Currently it is efficient enough but not reliable enough for researcher to go and confirm the references.
Aqueel
I already joined in but I’m unable to check this product. Is there a way I can also contribute as a tester?
Michael,
Thank you for your interest in participating in the Wolfram|Alpha project. Please click here to apply to be a tester. Thank you.
Very interesting, thanks
greeting and congratulations .
I think what you are attempting and accomplishing is nothing short of amazing.
I really like your blog and i respect your work. I’ll be a frequent visitor.
allows negative 1998 weather particular 1979 primary
K.I.S.S.
NKS is complemented by NKI (a new kind of intelligence)
… which in turn is complemented by NLH (a New Level of Hyperbole)
I notice that you say “We pushed very hard to get it launched before the summer so that we could spend the “quiet time” of our first summer steadily enhancing it, before more people start using it more intently in the fall.”. As your site reminds us, the Earth’s axis is tilted from the plane of the ecliptic. But the Internet is everywhere. “Quiet times” maybe, but “summers” never.
Thanks for the update Stephen, really enjoyed reading!
Wolfram Alpha and Mathematica are incredible products, opening new avenues to answers never before available.
The enhancement I’d like to see: When Alpha presents a graph, such as for weather temperature forecast, I’d like to be able to access the underlying DATA, and not simply an image file of the graph.
Thank you and best of luck in further developments.
Nicholas Kormanik
http://www.Kormanik.com
I’d like to see a modern design performing the intended purpose of the Dewey Decimal System. This would require manual human categorization. This could be implemented as a relational system in that the searcher could drill down through multiple hierarchical trees and then cross link the boolean intersection of those drill-downs.
Automated search of words or phrases scales well but omits the context which the above proposed architecture would provide.
Wolfram Alpha is deducing context and doing it remarkably well, but a hybrid approach could determine actual statistics of which approach or combination is actually working best in practice.
This whole idea could result in reintroducing the serendipity of cross correlation of seemingly unrelated data. That phenomena is at the root of the “Ah Hah” moments of scientific discovery.
I “dig” your idea, Don, as musicians would say. Keyword search is the holy grail.
Thanks a lot for update, proffesor.
I think it should be able to give more information when entering two companies or somthing like that. Still works great!
Great idea, it has many applications and great potential for adoption by many communities. Originally I found it difficult to enter in valid parameters/queries but now with so many examples available it’s getting much easier.
Please continue to work on the query language.
This page in very interesting and help to understood The importance of having a page with the capacity and versatility of this, thanks for you contribution of the knowledge
You need to integrate a natural language processing engine to handle queries. One suggestion I have is to build a dynamic chat bot that can understand, in a sense, what is being asked. The Simms project has built this kind of bot and it fools almost everyone that it’s a human during online chats. Integrating this kind of interactivity or simple understanding of what is being requested would help your site tremendously.