I am looking to decode intents from many strings from many conversations I have stored in a database, so I can use machine learning to create an intelligent chatbot. I have heard and tested tools like Amazon Lex, but I am looking to receive the intent from a string not create my own intents. Here is a sample starting question from the data I am working with:
Hi, can I please find out the location of the nearest Depot to Meadow Springs WA 6210?
Is there any chance we could get 34 cases from Melbourne to Sydney by Friday. I am hoping it will be a Sydney to Sydney tomorrow but if not can anyone do this by Friday from Melbourne?
can you tell me how the warranty claim is going on booking number 9528 thanks
Intents are usually created for a specific application by providing examples. However, some services do provide pre-defined intents you can use.
LUIS provides prebuilt "domains" which include some place related queries
Snips has an "intents library" that you can use
That may be able to get you started. If that doesn't work, this guide to a from-scratch implementation may be useful.
Related
I am looking at Articulate to support my own application. I want my users to be able to use Articulate to create the E-learning and then uploading the files to my site and run it on my site.
However i wish to store both the questions and the answers of the quiz that is created in articulate.
Does anyone know how this is possible or know a way around either by using excel or any other software to store the Q/A?
There may be more than one answer. But Articulate is SCORM compliant. It is designed to return test scores to the server using SCORM. I have not been involved with receiving those test scores by acting as an LMS, but in the past I have made custom applications that send that data to the LMS using scorm. But if you research SCORM and other APIs they use you might find something useful.
For example, if you mean Articulate Storyline then you can test send/receiving data using this package:
http://www.articulate.com/support/storyline/how-to-use-the-scorm-test-suite
This shows that it can be done. But you would have to write your own program to communicate with Storyline. If you can duplicate how that package works you might be on your way.
As an alternative to SCORM, you can also use the xAPI see https://xapi.com/overview/ to store your e-learning data
I am trying to build an iphone app that finds the location with business name.
For example, I want to annotate a restaurant and I want to find it with the name of restaurant. I was trying to use CLGeocoder, but it seems like geocoder does not help in this case. I am not sure what to do.. can anyone give me a hint about this?
Thank you
Google maps will take a business name and return location(s). It sounds like a webservice is what you're needing, you'll just have to think through the inputs, the outputs, and figure out how it all logically fits into your app.
"Business name" is info independent of the address and not available to CLGeocoder. For this you have to use an external service where business names are actually registered. I would suggest the Google Places API, but the search results will still be limited to those businesses registered to Google.
And yes, you will have to dirty your hands with "NSURL stuff", and process the results with "NSJSONSerialization stuff".
If you're happy to consider an SDK-based solution, Huq Industries offer exactly this as part of their Real-world Analytics platform. They've done a lot to address the problem of reliably relating device location to physical businesses accurately by combining location with other data including WiFi. You can get business events by business name, category and address.
Coverage is pretty global and it's mostly free. Check out the SDK repo on GitHub.
Disclaimer: I contributed to this.
I have been working with Carmen http://carmen.sourceforge.net/ for a while now, and I really like the software but I need to make some changes inside the source code.
I am therefore interesting in some students reports/projects there have been working with Carmen, or any documentation of the source code.
I have been reading the documentation on the webpage for Carmen, but with all respect I think the literature there is a bit outdated and insufficient.
ROS is the new hot navigation toolkit for robotics. It has a professional development group and a very active community. The documentation is okay, but it's the best I've seen for robotic operating systems.
There are a lot of student project teams that are using it.
Check it out at www.ros.org
I'll be more specific on why ROS is awesome...
Built in visualizer/simulator rviz
- It has a record function which will record all of the messages passed out of nodes, this allows you take in a lot of raw data store it in a "ros bag" and then play it back later when you need to test your AI, but want to sit in your bed.
Built in navigation capabilities,
-all you have to do is write the publishers of data for your sensors.
-It has standard messages that you need to fill out so that the stack has enough information.
There is an Extended Kalman Filter which is pretty awesome because I didn't want to write one. Currently implementing it, i'll let you know how that turns out.
It also has built in message levels, by that I mean you can change which severity of print messages are printed during runtime, fairly handy for debugging.
There's a robot monitor node that you can publish the status of your sensors to and it bundles all of that information into a GUI for your viewing pleasure.
There are some basic drivers already written. For example SICK lidars are supported right out of the box.
There is also a built in transform function, to help you move everything to the right coordinate system.
ROS was made to run across multiple computers, but can work on just one.
Data transfer is handled over TCP ports.
I hope that's more helpful.
For a web app I'm working on, I need to know the lat/lon of about 300 US cities. I also need to know the lat/lon for every US zip code.
Does anyone know of a free source to get this information?
Freebase will likely be able to help you. Here is New York and it has Lat/Long.
The Wal-Mart Expansion video used Freebase to get it's data, and it sounds like you're doing something similar.
Take a look at Ben Fry's Zip Code Visualizer. This is part of his book Visualizing Data.
There is an online database at Geocoder.us. And a simple perl module (we added a soap service to this so we could simply access it from any language, and the longest part of the development process was downloading database (it's about 4 GB).) The geocoing database is available from the US census bureau, a good article on getting this setup can be found here.
I am trying to develop an online translation service (sort of a personal challenge) but I have been looking for any guidelines or any way to see how it should be done and so far I have come up with nothing so. In a nutshell, does anybody knows where to find a service, code or explanation of how online translation works and/or guidelines for making one?
You could take a look at a similar project: Machine Translation
For a "personal challenge" this project seems way too big. You would need a huge dictionnary and very sophisticated translation algorithms.
Or are you asking if there are APIs to existing translation services?
Decent online translation services work as follows:
Email company with text to translate
They get humans to translate it.
Company sends translated text back in another email
At some point in the above, money exchanges hands.
Automated translation services tend to not work well, due to the huge amount of information required to translate text other than just the text itself, and issues that arise when there isn't an accurate translation for something between 2 languages.
This is a big undertaking. For personal use I use google translate. It does not do a great job, but enough I can get a decent understanding. At work we use COMIDOC, a fairly expensive commercial service. Its not perfect and we have to do a lot of work setting up specialized translations of technical sentences.
You can have a look at the codes of Spanish English, which is an online translation site.