Recent announcements of a bot framework for Skype from Microsoft and Messaging Platform for Messenger from Facebook just heated up the space around chat as a new platform that goes after mobile apps. More and more developers are coming up with an idea to make their own bot for Slack, Telegram, Skype, Kik, Messenger and, probably, several other platforms that might pop up in the next couple of months.
Thus, we have a rising interest in the yet to be explored field of making smart bots with AI capabilities and conversational human-computer interaction as the main paradigm.
In order to build a good conversational interface we need to look beyond a simple search by a substring or regular expressions that we usually use while dealing with strings.
The task of understanding spoken language and free text conversation in plain English is not as straightforward as might seem from the first look.
Below we look at possible dialogue structure, how to understand the concepts behind advanced natural language processing tools, and look into details on the platforms that we can use for our bots today through the API – LUIS from Microsoft, Wit.ai from Facebook, Api.ai from Assistant team, Watson from IBM and Alexa Skill Set from Amazon.
A Dialogue Example
Let’s look at the ways we can ask a system to find ‘asian food near me.’ The variety of search phrases and utterances could look similar to this:
- Asian food near me please
- Food delivery place not far from here
- Thai restaurants in my neighborhood
- Indian restaurant nearby
- Sushi express places please
- Places with asian cuisine
But if we are curious enough we can also ask Google Keyword Planner for other related ideas and extend our list by about 800 phrases related to the search term “asian food near me”. We use Keyword Planner for such tasks here because it is a great source of aggregated searches that users regularly do in Google.
Of course, not all of this is directly related to the original search intent, asian food near me. But given the results we see, they are still highly relevant to the service that we want to provide to the users; let’s say, for example, a curated list of Asian Food places.
So therefore we can try to steer the conversation towards the desired ‘asian food’ topic with the help of questions and suggestions from the bot.
Consider the next dialogue examples and a way to direct the conversation:
From the example above we can see how broad the variations of utterances can be that user can use for the intent to find food.
Also notice how users can say ‘Yes‘ and ‘No‘ during the dialogue for confirmation or decline of the suggested option.
As we just saw, we need some way to understand the language and conversational phrases that are more sophisticated than just a simple text search by phrase or even regular expressions.
Dialogue Structure as NLP engineers see it
From the example above we can see that each expression from the users has the intent to take some action.
An Intent is the core concept in building the conversational UI in chat systems, so the first thing that we can do with the incoming message from the user is to understand its Intent, this means mapping a phrase to a specific action that we can really provide.
Along with the Intent, it’s necessary to extract the parameters of actions from the phrase. In the previous example with ‘asian food’ words ‘nearby’ or ‘near me’ correspond to the current location of the user.
Parameters, also called entities, often belong to a particular type. Examples of entities types that are commonly supported in language understanding systems are:
- Enumeration (predefined list of named things)
Here are the basic representations of the Intent, Entities, Parameters as well as Sessions and Contexts which we will discuss later.
A Session usually represents one conversation from beginning to end. An example of one session is when you order the flight you start from: ‘I need a flight to London’ (the intent), then through subsequent interactions (questions and answers) you get the information about a booked flight and finish the interaction.
For storing the intermediate states and parameters from previous expressions during the dialogue we usually use context. We can think about context as a shared basket that we carry through the whole session and use it as short term memory. For example, during the flight booking chat we can store the intent BookFlight in a context and subsequently add other parameters (like, , or ) from the conversation once we get them from the user).
Unlike a session we can have many contexts during one conversation that nest one into another. Let’s say, after the user expression that represents theintent, we started a new context which indicates that we are currently collecting all parameters needed for the booking.
After the question about flight dates, the user decides to request info from the calendar, thus expressing a new intent, and starting a new context, , that saves the state of user interaction during the dialogue about events in a calendar. The user can even decide to reschedule several events and write a short email to involved parties with apologies and a reason for rescheduling, thus creating another nested context object, .
So some of the technical tasks of the chat bot app (or conversational agent) are:
- Understand the language in a plain text (or voice translated into text) as well as the Intent with Parameters.
- Process the Intent with Parameters and execute the next action to continue a dialogue with the user. (Result is a response or a subsequent question to continue the conversation by getting more data from the user and filling needed parameters in order to fulfill the action).
- Maintain the Context and its state with all parameters received during the single Session in order to get the needed result to the user.
Next, we will look at how available tools can help us with all of this.
Microsoft Language Understanding Intelligent Service (LUIS)
LUIS was introduced during this year’s Microsoft Build event in San Francisco together with Microsoft Bot Framework and Skype Developer Platform which can be used to create Skype Bots. In this article we leave aside Bot Framework and look at language understanding features from LUIS.
LUIS provides a concept of Entities that you can define and then teach a LUIS system to recognize from a free-text expression. There are also Hierarchical Entities that are helpful for recognizing different types or sub-groups. For instance, aentity can have and which can be recognized separately.
Currently, there are limitations of up to 10 Entities of each type per application, which will be enough for a middle-size service.
Besides Intents and Entities, there is also the concept of Actions that can be triggered by the system once the Intent and all required parameters are present.
Moving closer to the automatic language understanding and acting upon completion of Intents with parameters there is another feature called Action Fulfilment, which is currently present only in preview mode, but you can already play with it and plan for the future. The idea is that once we have an Intent then the system can automatically execute predefined Channel Actions like, or your own to an arbitrary API.
Dialogue support, which also presents only in a preview mode, can help us to organize the conversation and ask relevant questions to the user in order to fill in the missing parameters for the intent.
To train the model with different utterances, LUIS provides the Web interface where we can type an expression, see an output from the model, and make changes in labels or assign new intents. Additionally, LUIS stores all incoming expressions in the Logs section and provides semi-automatic learning features with Suggestion, when the system tries to predict the correct intents that are already present in the model.
Once we have the trained model, we can use the API to ask questions and receive intents, entities and actions with parameters for each expression as an input.
LUIS has the export/import feature for the trained model in a plain JSON with all expressions and markups for entities, which we then can repurpose in our code – or even substitute LUIS completely, if we decide later to build our own NLP engine.
Currently, LUIS is in beta and free to use for up to 100k requests per month and up to 5 requests per second for each account.
Next we will look at Wit.ai from Facebook.
Facebook Wit.ai Bot Engine
Wit.ai, an AI startup that aims to help developers with Natural Language Processing tasks through the API, was acquired by Facebook in January 2015. During the F8 conference in April, 2016 Facebook introduced the major update to their platform and rolled out their own version of Bot Engine that extends a previous intent-oriented approach to the story-oriented approach.
Building the conversation interfaces around story feels more natural and easier to follow than separate intent string by the context variable. Under the hood, during the logic implementation, you still work extensively with the context and need to do all tasks required to maintain the conversations correct state.
In Wit.ai we can use Entities, Intents (its actually just a custom entity type here), Context and Actions concepts that together form the model based on Machine Learning, and statistics can be used later for understanding the language.
On the bot side, during the story definition, we can execute any action that we might need to fulfill the context, user action, and prepare data and/or states in the context. Effectively, the Wit.ai Converse API will resolve the user utterance and the given state into the next state/action of your system, thus giving you the tool to build a Finite State Machine that describes sequences of speech acts.
However, all actions are executed on our server, and Wit.ai just orchestrates the process and suggests the next call of state mutations based on the model that we’ve trained.
Everything, from understanding the user inputs to the training expressions and list of entities, is available through the extensive Wit.ai API.
Like other systems, Wit.ai provides a handy Inbox feature where you can access all incoming utterances from the users, and labels them if they were not recognized correctly.
In one of the latest updates, Wit.ai introduced the chat UI for testing conversations so we can see steps that systems recognize, which helps during both the creation and the debugging of the model.
Wit.ai supports 50 different languages including English, Chinese, Japanese, Polish, Ukrainian and Russian.
Projects could be Open or Private, without any apparent limitations. Open projects can be forked and you can create you own version of the model on top of existing community projects.
The Wit.ai API is comletely free with no limitations on request rates, thus it is a good choice for your next bot experiments.
Api.ai – conversational UX Platform
To give you a better understanding of how API is different from other platforms. Here is the answer their CEO gave on Product Hunt:
Indeed, the service provides all the features you might expect from a decent conversational platform including support of Intents, Entities, Actions with parameters, Contexts, Speech to Text and Text to Speech capabilities, along with machine learning that works silently and trains your model.
Everything starts from Agents that represent the model and rules for your application.
The interesting thing is that API.ai has built-in domains of knowledge (Intents with Entities and even suggested Replies ) on topics like small talk, weather, apps or even wisdom. It means that your new Agent on the system can recognize these Intents without any additional training – and even provide you the response text which you can use as the next thing your bot will say. There are up to 35 different domains with full English support and partial support for the other six languages.
When you create an Intent, you directly define which Context the Intent should expect and produce as a result. Also, you can define several speech responses which an agent will return to your app through the API, so you don’t even need to store such variations in your app.
Api.ai provides integrations with different bot platforms including Slack, Facebook Messenger, Kik, Alexa and Cortana.
For example, you can build the conversational flow completely on the platform and then deploy it automatically on Heroku, or use a pre-built Docker container with the app.
Also, there is an embedded integration mode available so you can have an agent that works without connection to the internet and is independent from any API. Just think about use cases like embedded hiking assistants or in car assistants.
Api.ai looks like a decent solution that you can use for building sophisticated conversational interfaces. Alas, unlike LUIS-beta from Microsoft or Wit.ai from Facebook, it is not free but the basic paid version starts at 89USD per month. Their free tier is available, but is only good for experimenting and very small internal projects.
Amazon Alexa Skill Set
It only works with Amazon Alexa. Which at first glance looks like the simplest language processing algorithm available among all other systems, but it’s deployed, tested and exposed to more than 3 millions of Amazon Alexa users who already are using conversational interfaces on a daily basis.
With Amazon Alexa Skills Kit you can define Intents and Entities for your task. Alexa system recognizes an intent correctly with variations in words only when you provide every possible example of expressions that could exactly match how users might say it to Alexa. It feels like they are still working on their own version of machine learning in order to simplify the work needed for model training.
The great thing is that a whole new skill for Alexa could be easily built with AWS Lambda functions that seamlessly integrates with the Alexa Skills Kit.
Anyway, Amazon Alexa Skills Kit is an outstanding system that you should keep in mind and follow their development, because Amazon is currently a leading household platform for conversations and custom bot integrations, which they are aggressively pushing forward with new device offerings and features.
IBM Watson Developer Cloud Services
You probably remember the famous IBM Watson’s game when it won against two humans on the TV quiz show “Jeopardy” in 2011. So the good news is that IBM moved the technology behind the Watson into the cloud and released the set of API that you can use in your own conversational applications.
The API set includes language understanding offerings from a natural language classifier to concept insights and dialogue processing. There are a lot of building blocks that you can use in your application, but you probably will spend a decent amount of time integrating them into one solution.
We’ve used IBM Alchemy Language for sentiment analysis and keywords extraction for our experiments and it worked well. We think that IBM’s solution is the ideal choice for enterprises that want to be 100% sure of their API provider.
For a recent IBM Watson demonstration you can watch a fireside chat with Dr. John Kelly, who leads the Watson team at IBM, at TechCrunch Disrupt 2015 in San Francisco.
Also, IBM Watson is a costly solution and you can expect to pay up to $0.02 per API call in Dialogue API, so it may be too expensive to experiment with in building bots for Facebook Messenger when you still don’t have a working business model.
The full list of available API’s from IBM Watson Developer Cloud are available here.
As we just saw, there are various systems that we can use for building conversational interfaces.
Our personal preferences goes to Wit.ai from Facebook and LUIS from Microsoft – as they have all necessary elements for building conversations and they are free. At least for now, so you don’t have to worry about the price.
Anyway, we would recommend you store all data needed for your model in a structured way in your own code repository. So later you can retrain the model from scratch, or even change the language understanding provider if needed. You just don’t want to be in a situation when a company shuts down their service and you are completely unprepared. Do you remember Parse?
For the end-to-end solutions that you can use with less code, we think Api.ai is the way to go. If you need the embedded capabilities as well so as not to depend on an internet connection at all.
Alexa Skills Kit is proprietary for Amazon Echo devices, therefore, you can’t use it with arbitrary bots at Slack or Facebook Messenger for language processing, but it is ideal for smart home bots that augment your kitchen or living room environment, and which are built specifically for Alexa.
IBM Watson will work smoothly in an enterprise environment when you need to feed large amounts of data, and you have a decent budget and want to have a reliable and proven service provider behind you.
Generally speaking, we expect to see many more platforms and API services for language understanding tasks in 2016 because the field is just heating up with the major platforms announcing their bot platforms and frameworks. We still want to hear something from Apple about Siri integrations on WWDC and from Google about the new capabilities of Google Assistant for developers and possible ways of integrations.
Building our own bot
This article was written as a part of our own challenge to build a smart bot with AI capabilities that can help people understand how to build a mobile app, give useful advice and provide an estimation of development and design costs.
If you want to be notified about the next article on bot creation, you can sign up for our newsletter below.
More article about bots:
- The Rise of Chat Bots: Useful Links, Articles, Libraries and Platforms
- Why is everyone building chatbots? And how can they help me?
- Know Your Bot, Part I: Telegram And Twitter