After setting up the IBM Watson Conversation service on my Raspberry Pi today I was disappointed to see that I'd have to write out every possible input (intent) and output (entity). Chalk this up to my extreme naivety around machine learning, But isn't there a way to tie into an existing set of conversation capabilities?
For example, I'm sure Watson already knows all the words for Hello and their proper responses. Or how to answer a variety of silly questions. Is there any way to tap into the Watson we all saw on Jeopardy?
Thanks for your help!
There are a number of options here.
System Entities
These are pre-defined to allow you to understand certain common concepts. Numbers, Currency and Dates are the available ones at the moment, but there are more coming.
Entites
You can also pull public lists and import as CSV. For example: http://data.okfn.org/data/core/country-list . You may need to check the licensing before using though.
Intents
As you mentioned there is no pre-defined intents. But there are two solutions available that augment conversation.
First is "Watson Virtual Agent". This is a SaaS that contains pre-defined training sets for certain industries, as well as custom UI you can slot into your application. It's not cheap, but you can get a trial to play with it.
The other option is "Project Intu". It's still experimental, but it's purpose is to help in building robots/IOT devices. It contains pre-defined chit chat and some off topic stuff.
They have a "TJ Bot" project which can be used with a raspberry pi.
Related
I have a web background majorly with javascript, I have started learning Corda recently for project implementation and need guidance in this regard,
So our application is based on the web, the user signs up with different school name, create question papers, and then want to share either part of it or whole with teachers of some other school in our platform. they can make changes and assign it back to creator and the process goes back and forth, finally signing the paper to be finalized, once finalized it cannot be changed by anyone. I need to store these transactions in Corda application, not sure how to go about it, I did try replicating it using negotiation application in corda/kotlin/sample, but stuck in a bug as I was trying to send a list of objects.
I do have the following questions in mind
Should I use enterprise edition or go with open source as I think I need schema design for this. web db is in postgress
As far as I have seen each node is predefined in the config with username and password,is there a way to create the node while the user signs up.
I have schools and teachers inside the school, do I need a separate node for each school and then create states in each node(not sure if a node can be set up at run time). or do I use the account's library provided for creating the account of each teacher, if yes id there a way to use passwords in it, unable to find password field in it.
how do I send an array of objects to the state, or should I create a separate state for each question, as different questions can be assigned to different teachers, but again multiple questions can be assigned to the same teacher.
These are few questions on my mind any help is much appreciated, as most of the examples gave IOU samples or states with int and string, Please guide me in the right direction.
Alessandro has good advice here, definitely look at the samples repos for inspiration on how to build what you're looking for.
start with open source, it's easier to prototype and you can switch to enterprise later it won't be an issue for you
this depends on design, you wouldn't really want to create a new corda node per-person, you might want to have corda accounts that run on a single node instead. See accounts sdk here: https://github.com/corda/accounts
what you might do is make a corda node for each school and then accounts per teacher like you were already were thinking. That would mean only a couple of nodes based on the number of schools you have.
as long as your state is marked with #CordaSerializable you won't have problems sending arrays of data, I send an array in a state in this sample here: https://github.com/corda/samples-java/blob/master/Advanced/secretsanta-cordapp/contracts/src/main/java/net/corda/samples/secretsanta/states/SantaSessionState.java#L24
https://github.com/corda/samples-java
https://github.com/corda/samples-kotlin
Currently i am creating a design for a new enterprise application. Right now we have a lot of different proprietary solution and we wanna create a new one to switch from them all.
Briefly it is a kind of data destribution system. We have a lot of clients who needs a lot of different data.
What do i want:
1) Common REST API service
2) Some synchronoyu(async?) enviroment to send task and get data back. On image below you could see i think to use spring kafka request/reply template. It helps to scale my application in future.
3) Different typec of calculators for every kind of data
I search a lot how to do the second point the best way but didn't find any ready solutions or advices. Is it good to use kafka here? Maybe some one could give me advice about best practice in such situations.
Plz, send me links for articles or something else, because it will be a big application and i wanna start to create it rightly from the beginning.
I am working on a chatbot that uses both Watson conversation and NLU. My chatbot is designed to provide information about other people - friends, colleagues (ex: their current position, contact number etc.,). Chat bot isnt able to recognize few names as persons. How do I handle this situation ? Any thoughts ?
NLU does recognize person pretty good, if you are using Watson Conversation along with NLU, I am not sure how you are combining both of them. Can you explain it a bit more?
I faced a similar situation using NLU, here are the few ways I overcame it
1.NLU relies on context, instead of sending smaller texts, send bigger texts.
2. It also relies on Grammatical features, usually having correct punctuation, First letter capital names for Person, City Names helped me get better results
I have a basic model set up but it appears that the Alexa beta builder expects the design of the model to be up front with explicit lists of possible answers to requests. However, the Jeopardy game on that platform appears to allow new answers from day to day and I am supposing they don't need to update their model each day. Can someone shed light on this process?
I would like to be able to:
Launch intent to start conversation
Handle back and forth within web service response and request
Handle basic stop/start from Alexa
How does the middle portion (response/request) get modeled up front?
Currently, you need to provide a list of expected values for each of your slot types (a slot type may be question_response in this case).
Not sure how Jeopardy works but I have a couple ideas:
They provide huge lists of possible answers (and they update them from time to time). I bet there is no one writing new questions every day, they have a pool of questions and they can anticipate the answers to those.
They have access to an API that is not open to the general public (as do people who are participating in the social bot challenge) or are allowed to use the deprecated LITERAL slot type.
I'm a statistician by trade and I'd like some recommendations on how to set up a website that can collect data into a database. For personal use, I use Google Forms to collect data, and everything gets populated into a spreadsheet. However, this may not be appropriate in a more professional setting, especially when we have multiple pages/forms. I imagine two uses:
A website where I can send the link to others so they can fill out, similar to Google Forms.
A website where only authorized users can log in to fill out data. Think of a setting where patients are followed periodically in a research study. It'd be cool to have the clinician enter the data directly into the database as he/she fills out the forms as opposed to having another data analyst transcribe his written forms into the database.
The obvious solution would be to hire a web developer. However, I like doing things myself when they are manageable. I imagine a web developer would have to know html, php, and database knowledge (eg, MySQL or PostgreSQL). My experience in these are limited to setting up a wordpress blog on my linux server. My experience with html is also limited as I use emacs org-mode to generate them from plain text. I hope to hear about solutions with a minimal learning curve. My preference of course would be free open source software and Linux-based, but I'd like to hear all available solutions (our data manager is a Windows user).
I recently read a post on Linux Journal that mentions REDCap, but it seems you have to get institutional permission to use.
I also tagged "R" on this post as I'd like to hear what R users are doing about data collection. I'll ultimately analyze the data with R, but all data analysis begins with the scientific question and data collection.
Thanks!
UPDATE 10/4/2010: Thanks everyone for the responses so far. It appears most of the third-party solutions proposed so far has data housed in a database hosted by the vendor. I'd like to house all data in our SQL Server. That is, data entry from the web enters the database in real time, ready for data analysis.
Maybe the limesurvey.org project is of interest ...
It sounds to me like you've got yourself a med study. There are a plethora of concerns that come to mind just from what you've described you want to do. Not the least of which is privacy. Where is it going to be hosted? Have you received consent from the patients to be collecting and transmitting their information electronically? What data are you storing, if any, that could combine to present their identity.
Personally, I steer clear of DIY online data collection tools. I pay a firm, like Ipsos, Research Now/E-Rewards, to program and manage data collection using questionnaires that I have designed. The reason is, knowing how to design research and analyze data is one thing. But if you've been trained in statistics - I can safely argue that you "don't know shit" about data collection. Sure you may know a bunch about sampling theory, but when it comes to getting data in - it's best to leave it to the pros.
There are a number of "industrial quality" online data collection tools available.
Confirmit (Pretty much the gold standard for online data collection)
DASH (Smaller following, but incredibly flexible)
There are also purely web based solutions, some of which are free (not that I would recommend using them)
QuestionPro
SurveyMonkey
Zoomerang
Although, unless you're doing a study with over 50 patients, I would just recommend getting the Physicians or their assistants to fill out Excel sheets and send them to your co.
Also, it's unlikely that you'll need to set-up a username/password system. What you want is referred to as an "open-link". Where respondents click a link and enter information, identifier info can be added by the respondent. You don't need a password because people can only INPUT information, not read it.
Most of the systems I mentioned above work on the idea of emailing a respondent (a clinician) with a link to a web based survey. Which could be easily adapted to your specific needs and act as a reminder to the clinician to fill out the form.
If your question types are simple. I'm sure you could hire a programmer to put together a website that has the forms you need behind an authorized front end. PHP/MySQL would likely do the trick. But, I would double check the privacy laws in your jurisdiction surrounding medical research before going ahead.
I have conducted medial research using an online form (actually two of them). My questions were quite discrete and particular to the disease I was researching.
Previously in a related project, I had created two or three page questionnaires which were printed and then subjects and surgeons filled out the forms and our research coordinator would enter them into our database. It was a lot of work with lots of room for error. I did not like it. Online forms were much better.
I used SurveyGizmo and was happy with it. I looked at lots of options about two years ago. Google Forms did not exist at that time. I went with SurveryGizmo primarily because they had a a statement (attestation) that they were compliant with HIPAA. I could not ensure security such as ssl connections with the other websites. However in order to get myself into that capability (https connections) I had to buy the enterprise level eventhough on every other capability I could have used the free service. Also SurveyGizmo offered a 50% reduction for non-profits which our research institute qualified for.
SurveryGizmo was easy to design and put into production without having to program myself. It was easy to download the data in csv format and read that straight into R. Although I had some weird issues that I needed help with. I had to use the "old" format for export so that it came as a straigtforward csv. Furthermore, the csv file had the odd feature of the the first TWO rows being header rows. But I solved that problem with the help of stackoverflow.
SurveryGizmo has fantastic logic and piping that enbabled me to only ask relevant questions and thereby not waste the time of my respondents and even more importantly, there were no irrelevant questions to confuse respondents.
Finally, I was able to use SurveyGizmo in such a way that I could also track our (research staff) fulfillment and logistics. For instance we got notification when there were new potential subjects who were interested in participating. We were able to note FedEx tracking numbers along with the records of the corresponding subjects.
Basically it worked well.
The safest platform for collecting confidential survey data is Confirmit. There is a learning curve involved here- you will be coding in VisualSQL, which is only used in Confirmit. The survey responses will export to csv files, where you can analyze your results in R.
If you are collecting any confidential data, or data where respondents need unique access links so they can only see their own version of the survey, you will want to use Confirmit. The data is housed in Confirmit's data center, but their data is much more secure than other vendors (i.e., a third party will not be able to hack into your survey and see an individual's responses, or intercept the data that is being sent from your respondent to Confirmit).