When creating a AI talking bot what kind of methods of design should I use? Should it be one function, multiple modules, should it have classes?
Understanding language is complicated, so the goal you need to determine first is what aspect of language you want to understand.
An AI must be able to understand what the person says to it, then relate it to what it already knows, and then generate a legitimate response.
These three steps can all be thought of as nearly independent, so you need to address each on its own.
The brain, the world's best language processor, uses a Neural Network, but that's not likely to work well for you.
A logic-based proof solving system, where facts that follow from facts are derived would probably work best, and I know of at least one system that uses it fairly effectively.
I'd start with an existing AI program (like the famous Eliza) and run its output through a speech synthesizer.
Some source for Eliza is available here. One open source speech synthisizer is FreeTTS.
If you're using a language other than Java, there are similar candidates AI bots and text-to-speech code out there.
I've started to do some work in this space using this open source project called Talkify:
https://github.com/manthanhd/talkify
It is a bot framework intended to help orchestrate flow of information between bot providers like Microsoft (Skype), Facebook (Messenger) etc and your backend services. The framework doesn't really provide implementation for the bot providers yet but does provide hooks into its natural language recognition engine.
The built in natural language recognition library can be used to classify sentences to topics which you can then map to skill functions.
Give it a try! I'd really like people's input to see if how it can be improved.
Related
I'm trying to implement a collaborative canvas in which many people can draw free-handly or with specific shape tools.
Server has been developed in Node.js and client with Angular1-js (and I am pretty new to them both).
I must use a consensus algorithm for it to show always the same stuff to all the users.
I'm seriously in troubles with it since I cannot find a proper tutorial its use. I have been looking and studying Paxos implementation but it seems like Raft is very used in practical.
Any suggestions? I would really appreciate it.
Writing a distributed system is not an easy task[1], so I'd recommend using some existing strongly consistent one instead of implementing one from scratch. The usual suspects are zookeeper, consul, etcd, atomix/copycat. Some of them offer nodejs clients:
https://github.com/alexguan/node-zookeeper-client
https://www.npmjs.com/package/consul
https://github.com/stianeikeland/node-etcd
I've personally never used any of them with nodejs though, so I won't comment on maturity of clients.
If you insist on implementing consensus on your own, then raft should be easier to understand — the paper is surprisingly accessible https://raft.github.io/raft.pdf. They also have some nodejs implementations, but again, I haven't used them, so it is hard to recommend any particular one. Gaggle readme contains an example and skiff has an integration test which documents its usage.
Taking a step back, I'm not sure if the distributed consensus is what you need here. Seems like you have multiple clients and a single server. You can probably use a centralized data store. The problem domain is not really that distributed as well - shapes can be overlaid one on top of the other when they are received by server according to FIFO (imagine multiple people writing on the same whiteboard, the last one wins). The challenge is with concurrent modifications of existing shapes, by maybe you can fallback to last/first change wins or something like that.
Another interesting avenue to explore here would be Conflict-free Replicated Data Types — CRDT. Folks at github used them to implement collaborative "pair" programming in atom. See the atom teletype blog post, also their implementation maybe useful, as collaborative editing seems to be exactly the problem you try to solve.
Hope this helps.
[1] Take a look at jepsen series https://jepsen.io/analyses where Kyle Kingsbury tests various failure conditions of distribute data stores.
Try reading Understanding Paxos. It's geared towards software developers rather than an academic audience. For this particular application you may also be interested in the Multi-Paxos Example Application referenced by the article. It's intended both to help illustrate the concepts behind the consensus algorithm and it sounds like it's almost exactly what you need for this application. Raft and most Multi-Paxos designs tend to get bogged down with an overabundance of accumulated history that generates a new set of problems to deal with beyond simple consistency. An initial prototype could easily handle sending the full-state of the drawing on each update and ignore the history issue entirely, which is what the example application does. Later optimizations could be made to reduce network overhead.
We are trying to implement a natural language search function using the IBM Watson Cognitive Insights (CI) service. We want the user to be able to type in a question using natural language and then return the appropriate document(s) from a CI corpus. We are using CI rather than the Watson QA service to avoid the need for training and to keep Watson infrastructure costs down (i.e. avoid the need for a dedicated instance of Watson for each corpus/use case).
We are able to build the necessary corpus through the CI API but we are not sure which APIs to use in what order to accomplish the most precise/accurate query possible.
Our initial thought was to:
Accept the user’s natural language question and Post that text string to the “Identifies concepts in a piece of text” API (listed 6th from the bottom in the CI API Reference document) to get a list of concepts related to the question.
Then do a GET using the “Performs a conceptual search within a corpus” API (listed 3rd from the bottom in the CI API Reference document) to get a list of related documents back from the corpus.
The first question - is this the right way to go about achieving our objective described in the first paragraph of this post? Should we be combining the CI APIs differently or using multiple Watson services together to achieve the objective?
If our initial approach is the right one, then we are finding that when we submit a simple question (e.g. “How can I repair MySQL database corruption”) to the “Identifies concepts in a piece of text” API we are not getting a comprehensive list of associated concepts back. For example:
curl -u userid:password -k -d "How can I repair MySQL database corruption" https://gateway.watsonplatform.net/concept-insights-beta/api/v1/graph/wikipedia/en-20120601?func=annotateText
returns:
[{"concept":"/graph/wikipedia/en-20120601/MySQL","coords":[[17,22]],"weight":0.85504603}]
Yet clearly there are other concepts associated with the example question (repair, corruption, database, etc.).
In another example we just submitted the text “repair” to the “Identifies concepts in a piece of text” API:
curl -u userid:password -k -d "repair" https://gateway.watsonplatform.net/concept-insights-beta/api/v1/graph/wikipedia/en-20120601?func=annotateText
and it returned:
[{"concept":"/graph/wikipedia/en-20120601/Repair","coords":[[0,6]],"weight":0.65392953}]
It seems that we should have gotten back the “Repair” concept from the first example also. Why would the API return the “repair” concept when we submit "repair" but not when we submit the text “How can I repair MySQL database corruption” which also includes the word “repair.”
Please advise as to the best way to implement a natural language search function based on the Watson Concept Insights service (perhaps in combination with other services if appropriate).
Thank you very much for your question and my apologies for being so late in answering it.
The first question - is this the right way to go about achieving our objective >described in the first paragraph of this post? Should we be combining the CI >APIs differently or using multiple Watson services together to achieve the objective?
Doing the steps above would be a natural way to accomplish what you want to do. Please note however that the "annotate text" API uses currently exactly the same technology that the system has for connecting documents in your corpus to concepts in the core knowledge graph and as such, it is more "paragraph" oriented rather than individual question oriented. To be more precise, the problem of extracting concepts in a smaller piece of text is generally more difficult than in a larger piece of text because in the latter there is more context that can be used to make the right choices. Given this observation, the annotate text API goes the more conservative route again given its paragraph focus.
Having said that, the /v2 API that we now have does improve the speed and quality of the concept extraction technology, so it is possible that you would be more successful in using it in order to extract topics from natural language questions. Here's what I would do/watch out for:
1) Clearly display to the user what CI extracted from the natural language in the input. Our APIs give you a way to retrieve a little abstract per concept which can be used to explain to a user what a concept means - do use that.
2) Give the user the ability to eliminate a concept from the extracted concept list (strike it out)
3) Since the concepts in concept insights currently correspond roughly to the notion of "topics", there is no way to deduce more abstract intent (for example, if the key to the meaning of a question is on a verb or an adjective as opposed to a noun, concept insights would be a poor way to deduce it). Watson does have technology oriented towards question answering as you pointed out before (the natural language classifier being one component of that), so I would take a look at that.
Yet clearly there are other concepts associated with the example question >(repair, corruption, database, etc.).
The answer for this and the rest of the posted question is in a sense above - our intention was to provide a technology first for "larger text" which as I explained is an easier task. Since this question was first posted and today, we did introduce new annotation technology (/v2) so I would encourage the reader to see whether it performs a little better.
For the longer term, we do have the intention to give the user a formal way to specify context for a general application so that the chances of extraction of relevant concepts increase. We also have a plan to have the user be able to specify custom concepts, as it has been observed in the past that some topics of interest to users are impossible to match in our current design because they are not in wikipedia.
I would like to make a bot that can carry on a simple conversation. I would like to be able to supply the bot with parameters about the things it knows and how it responds to certain subjects. I am wondering if anyone knows of any freely available source code or an API for a decent conversational bot.
I would like to use this to facilitate gaming by having computer-controlled characters that interact with the real players without having completely pre-scripted, static dialog. I am hoping that I can find something capable of holding a simple, generic conversation unless asked about a specific topic, at which point it can give specific replies to a pre-set list of specific topics.
I am asking more about the conversational-processing aspect and not so much about a front end or hooks to other apps or anything like that. Initially, I will just make this a local command-line based thing, then if satisfied I am looking into libpurple as an API to access various communication networks once I have the dialog processing ready.
So, does anyone know of any source code or API for something like this? Google brings up mostly tools for things like imified. I'm not expecting there to be a lot. A source code for something that exists that can handle various emotions and topics and such would be awesome, but I'd be happy with something that just holds the simplest of conversations, as there should be something somewhere that does this, seeing how there are multiple IM bots in existence.
In the absence of a good source or API, would anyone happen to know of any good materials about programming an AI that can have a conversation? Again, I'm not talking about PhD papers discussing robots that can pass believably as humans or anything like that; I mean materials that discuss some simple programming techniques that common conversational bots use to hold rudimentary conversations.
Because of the libpurple API, I'll probably be doing this in C++. So C++ resources are preferable but not required.
(edit) I just stumbled onto AIML (Artificial Intelligence Markup Language). I am currently looking into that, and it sounds like it might be promising, especially if there are any pre-made conversational resources available for it, as then I could just add topics to it in the manner I mentioned, if I am understanding it correctly.
AIML is old, obsolete and is a torture to create his database. I suggest you follow this gamasutra's article about chatbot languages. This article describes the ChatScript language, is a great alternative for AIML.
Another language is RiveScript that have a cool clean style, but it seem like a copy of AIML with the same bad concepts.
I'm developing the Aerolito language that is based on YAML, it's just a hobby project and it's not usable yet. =]
In my opinion, ChatScript is the best option for now.
I understand this question is old, but things have changed in the time since the question has posted. Check out the following projects, these bots learn from either text files, irc chat logs or in the case of triplie, they can read websites (albeit not perfectly).
triplie-ng: https://github.com/spion/triplie-ng
cobe: https://github.com/pteichman/cobe
Giorgio Robino mentioned http://superscriptjs.com/ but it's more than just chatscript - it's a superset of rivescript and chatscript and also includes a built-in triple store to implement WordNet etc.
I'm building an application as part of a course project which allows users to rate an place/event .
My basic question is how should I proceed in this ?
In what language should I write my code ?
If a user provides a 5-star rating, how do I collect it and put it in the database ?
Any guidelines on how to put the initial steps would be very helpful as my knowledge relating to web services is very weak.
Any help/pointers to more information would be very appreciated
Your question is overly vague and isn't related to system administration, so it's probably going to get closed once someone comes along with the appropriate privileges. However, as long as it's here...
My basic question is how should I proceed in this ?
If you are completely at a loss you may want to spend some time consulting with your instructor, who may be able to suggest likely sources of information and provide some direction for your work.
In what language should I write my code ?
You should write your code in a language with which you are familiar that allows you to fulfill the requirements of the project. Anything else will needlessly extend the amount of time it takes to complete the project. If your goal is to learn a new language, you face a mind-numbing number of choices. Python, Ruby, and PHP are all see wide use in web applications. On Microsoft platforms, .NET is quite popular. You will find proponents and detractors for all of them.
If a user provides a 5-star rating, how do I collect it and put it in the database ?
This looks suspiciously like you're asking us to do your assignment for you.
I'm interested in web development and by that I mean the bigger projects like facebook or twitter. I know the basics of java, css, php and mysql. I know there is a lot more out there. I read about it. But I don't know what the purpose is and how to put in place.
Things like: Scribe, thrift, casandra, Unix/Linux, shell/perl/python scripting, PostgreSQL, MongoDB, non-relational NoSQL datastores, JVM, nginx
I want to know why they need it, how they use it and what te purpose is.
What I need is a book like technical background of facebook for dummies or so.
Are there any books or websites that explain this from scratch?
Thank you!
EDIT:
Thank you for your answers! You have been very helpful. I was in the assumption, experienced programmers know almost anything about the technology there's used today. But as I read, you can only know so much and I need to figure out which technology to use. I take on the encouragement to start building small. And will take on php and improve my skills from there.
Thanks again!
http://highscalability.com/
This is one of the best sites out there. There are several case studies describing what and why many websites use, and pointers to further references. I would also look at the Google Scalability Conference 2007 talks
http://www.google.com/search?q=Google+Scalability&hl=en&client=firefox-a&hs=YUg&rls=org.mozilla:en-US:official&prmd=v&source=univ&tbs=vid:1&tbo=u&ei=fl4OTPUkorIwueCQxQw&sa=X&oi=video_result_group&ct=title&resnum=4&ved=0CDIQqwQwAw
It's all about choosing the right tool for the job in my eyes. There is so much technology out there it's impossible to learn it all. Just choose the subset that will work for you.
The best place to start is by building small simple websites, and as you come accross problems that you need solved you research the tools needed to solve those problems.
If you attack all of the areas at once, it's going to be overwhelming and you will not get anywhere.
For a general overview on what each of the technologies does, Wikipedia gives a good overview on most technologies.
If you are interested in database content which it seems like you are, a good place to start is reading up on normalisation.
Scribe, thrift, casandra, Unix/Linux, shell/perl/python scripting, PostgreSQL, MongoDB, non-relational NoSQL datastores, JVM, nginx
Those I would search on Wikipedia for to get a quick overview. Facebook is written in PHP/MySQL. There are some books on the subject of creating social networking sites, and some books have gotten decent reviews on Amazon.com, however, I have not read any of them myself.
If I were you, I'd start with PHP/MySQL and sit down and write a simple social network. Break the project down into components and tasks and Google for each challenge you encounter such as sessions, database structure, security, friend structure, and processing POST and GET requests.
You'll learn a lot and you get the big picture. Once you see the big picture, you can take another look at different technologies that are available and then decide which component you could have developed better with other tools. I personally don't think that looking too much into the technology available is good for someone who is still in the beginning stages. Start doing, learn from it, and then your questions become much more specific and a lot of things will make more sense.
The problem you're having is you're looking at smaller, specialty products, and not at larger, more mature technologies. Wikipedia will actually give you a decent overview of most of the medium-and-large projects out there.
Cassandra, Hadoop, Mongo, and NoSQL are all lovely... but they're specialty tools. SQL is a general purpose solution that works for 99% of the sites on the net.
Unix/Linux isn't a specialty tool; you might want to try going to Ubuntu's website and installing Linux, and just using it day-to-day, the way you'd use Windows. When you need to figure out something new, like setting up a webserver, do it on the Linux box and a Windows box, and you'll eventually learn linux pretty darn well.
As far as scripting, O'Reilly makes a great line of books on Bash, Perl, and Python.
JVM is a Java Virtual Machine, which is a core of getting Java code to go. Sun's website has a great set of tutorials on learning Java.
It might be much, much easier to pick a project (or three) that you'd like to learn, and learn some of these by doing. I'd probably suggest learning some SQL before learning the newly established alternatives; that lets you learn the rest of the system, as SQL is pretty easy. Once you've got the rest of the thing solid, try swapping in a NoSQL solution at that point.
There are a lot of frameworks that do a lot of different things. You've named a lot of different things from a lot of different areas. The best way to think of these things is to group them by category. Here's an example:
Suppose you have a laptop and you want to host a website. You'll need the following at a minimum:
1) Web Server software. Two popular options are Microsoft's IIS and Apache Web Server.
That's really all you need. You can set up your www_root folder and load files into it. Assuming everything is configured properly, you can now load HTML pages into that folder and access them through your IP address. Every page you view in your web browser is in HTML format. CSS is a stylesheet language that defines how your HTML will be formatted. You can also start writing Javascript, as most modern browsers support the client-side scripting language.
Chances are you'll want the following as well:
2) Database software. Two popular options are Microsoft's SQL Server and MySQL
3) Server-side scripting. PHP is very popular, as is ASP. You'll need the runtime deployed on your server. Python, Ruby, Perl, etc all fall under this category.
4) Web Application Framework(s). This will provide you with libraries for your language of choice to help develop web applications and websites. CakePHP, Ruby on Rails, and the Google Web Toolkit are examples of web application frameworks.
Additionally, you may want to utilize:
5) Additional libraries. JQuery, for example, is quickly becoming a popular library for Javascript that handles a lot of common tasks for you. Instead of writing complex effects code and what-not yourself, just use the pre-written code in the JQuery library.
6) Data interchange technology. If you are passing a lot of information back and forth, you will likely want to encapsulate this data in a logical format. Ideally, this format would describe the data and allow your applications to easily read/process it following a standard. This is where XML and JSON come into play.
I can't recommend a good book for you to learn this stuff, but I feel that the collective replies to your question here should be more than enough to get you started.
Ultimately, what you need to do is determine what technologies you need, and then choose the right one for the job. Don't go building an application using Ruby on Rails just because it's what Twitter used, but rather choose it because it provides some advantage to you over the other options.