This is the first batch of APIs that my team - the Watson Developer Cloud team - is exposing through IBM BlueMix for everybody to try and use. We have many more APIs in the pipeline but we decided to come out quickly with a small set to start with. We are trying get some early feedback from the developer community on what they find useful, what they'd like to see, how the APIs are designed, the quality of the documentation and example code, etc. Comments and questions are very welcome!
It seems that to get a true "wow" moment out of this, you would need to use the services in combination, but there is no demo of this. Each demo looks like nothing more than a database search of the training data - no super amazing algorithms supplied.<p>Perhaps IBM could provide an example "wow" moment to inspire us?
Most commenters here find these demos very underwhelming and I must agree with them. Well known open source NLP packages like Stanford NLP or NLTK do much better on these (very academic) tasks.<p>I think the problem is that Watson's demos have been trained for very specific and narrow domains (like "cloud services" in the case of Resonance). What we really want to know is how easy (or difficult) it is to train Watson for our own domain.<p>If Watson has to make assumptions on my domain, then it will be really hard to build something useful with it.
I don't understand what the heck IBM is up to. They have ads with a bunch of cool icons saying stuff about a smarter future world, but I don't know what to make of any of it. Like, "Wouldn't it be great if the doctor came to you <i>before</i> you were sick?" Um, I guess so?
How do these services work, compsci-wise? Could someone link a few IBM publications explaining how the Question & Answer API works? That would be very helpful. The documentation pages explain nothing.
The language detection failed to work (it identified it as tr-TR) with these words for Slovene: jabolko hruška sliva marelica drevo dež mleko malo preveč majhno veliko<p>This works perfectly on the first result on Google for "language identification", however: <a href="https://open.xerox.com/Services/LanguageIdentifier" rel="nofollow">https://open.xerox.com/Services/LanguageIdentifier</a><p>Edit: I now see Slovene is not supported, apologies are in order.
One challenge with trying to expose these kinds of services via an API is that much of their utility emerges from a building a model around data of interest. In order to efficiently build a customized capability, one would have to upload potentially large amounts of data to an engine for processing. As a general information service, you ask a question in text, and get an answer in text.
This is interesting!<p>I copied their own text from the top of the page at <a href="http://watson-mr-demo.mybluemix.net/" rel="nofollow">http://watson-mr-demo.mybluemix.net/</a> and selected "Cloud Computing." Then I changed all the words that were grey until they were green.<p>Original:<p>The Watson Message Resonance service analyzes the popularity of a given word within a specific community. By using this ranking system it is possible to recommend more resonant words to use when crafting messages targeted at specific audiences.<p>Changed:<p>The Watson Message Acceptance service analyzes the popularity of a given word within a specific community. By using this ranking system it is possible to recommend more effective words to use when A/B testing messages written for specific audiences.<p>-<p>Which one resonates more with you? :)
I'm heading up a project that will add a layer of text-based help to online courses (thats the short description...). I would love to explore the Watson APIs more. Aside from diving into the samples here, do you have other suggestions for learning more?
There seems to be a lot of context missing. I can't for the life of me come up with a simple example that demonstrates these services' value to me.
In the 30 second attention I was going to give, 20 seconds was spent on registering. And then 10s to figure our if there is any demo or any sort.<p>I couldn't find anything easy to find. I give up. Website is too slow too. And everything shows classic big corp red tapism.
So I can feed Watson public info about someone and it can make recommendations...for travel like the example, maybe preference of beverage, or custom dictionary words/terms that would be associated with this relevant information. Like a custom dictionary customized to an individual with a little alpha/numeric replacement and some special chars thrown in...wait I have to go ask Watson a couple of questions.
I tried the Language Identification service (<a href="http://ibmlaser.mybluemix.net/liddemo.html" rel="nofollow">http://ibmlaser.mybluemix.net/liddemo.html</a>), put in Vietnamese from wikipedia and "en-US" returned.<p>I did sign up. Note that in incognito mode, I have access to that link. I am guessing others do too.
Here is a link to the docs that should get you up and running with an example application pretty quickly.<p><a href="http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/doc/qaapi/index.html" rel="nofollow">http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl...</a>
For anyone that would like to leave feedback about what we can do to improve the API's feel free to leave your input here. Have at it!:<p><a href="https://trello.com/b/dXizfv9z/watson-developer-cloud" rel="nofollow">https://trello.com/b/dXizfv9z/watson-developer-cloud</a>
I tried the Relation Ship demo on the first paragraph of an HN frontpage story :<p><a href="https://imgur.com/7XYnttk" rel="nofollow">https://imgur.com/7XYnttk</a><p>It obviously has some way to go .