Can Machine Learning Use Knowledge instead of Data? Deep Cloning vs Deep Learning

ge2

Machine Learning (ML) field is defined by most people to be exclusively a field of data science, which is incorrect in principle. The main goal is to make computers perform cognitive skills similar to human brain and to immitate how human brain learns and thinks. Why use data only? Isn’t most of our learnings based on knowledge consumption?

Human brain learns mostly from knowledge, not from data!

As a result, we need machine learning methods that use knowledge directly. This area of research has not been explored as much as its data-driven counterpart (deep learning) because of the challenge of Knowledge Representation (KR) and the difficulty of computerized ontology creation.

KR methods such as semantic nets and logico-linguistic modeling have a long history of R&D using static/given knowledge but not in the context of “learning”. So, the question is how can we extend KR methods into a “learning” method? This brings us to the new idea of deep cloning where KR is molded into a neural-network-like structure poised for learning by reading.

Can Computers Learn by Reading?

reading

Knowledge-based learning methods make it possible for computers to learn by reading similar to how we educate ourselves. Once a deep cloning system is set, then a computer can start reading books (text) to learn a subject and answer questions about it. The trade off is between the difficulty of ontological (knowledge-based) learning versus the advantages of independence from training large data (corpus) and dealing with issues like convergence and generalization.

Advantages of Knowledge-based Learning
There are a number of advantages of this approach in comparison to data-driven methods as outlined below:

  • One-shot Machine Learning: Since knowledge does not require a supervised reference point, learning becomes one-shot machine learning devoid of convergence problems encountered in deep learning.
  • Not Stuck in the Past: Data-driven models require data collected from the past experiences. This makes them vulnerable in application to new things (i.e., new car, new plane, new drug, new house, new neighborhood, new disaster.) Knowledge-based systems are not biased by the past, and can employ new knowledge immediately.
  • Knowledge is Less Limited than Data: Availability and abundance of data do not guarantee its completeness, and data can still be limited in explain the process it comes from. Weather prediction is a good example. Knowledge, on the other hand, represents the best data experience available.

Fundamental Differences
In processing natural language and representing knowledge (after reading a text), deep cloning network (shown on the left) is comprised of layers with different objectives and different neuron functions. In contrast, deep learning (shown on the right) is a homogenous architecture of neurons dedicated to minimize the error at the output in a supervised mode of learning. Despite variations of deep learning, no neuron activity is designated for any linguistic role.

ge20

Knowledge representation on the left can be a one-shot process using only the text of the knowledge whereas learning on the right requires long training cycles using corpus way larger than what is needed on the left.

Answering Questions

6Image6

Knowledge-based machine learning can answer questions from the content it learned with utmost precision using the ontological connections shown in the network picture above. Shown aboveis a hypothetical case, where a question presented to the network finds its most relevant answer using those connections. In case of partial connections, the network puts more emphasis on target, event, and instrument (in this order) and produces answers with an accuracy score. Based on the type of application, a threshold can be set to declare “no answer” if the best scoring sentence is below the threshold. With such a capability, the chatbot becomes self-aware of its performance, and can report how well it did in answering questions. This can be further expanded to social learning where chatbots can ask for feedback to learn how to answer particular questions.

Knowledge Breeding

8Image8

More impressive than answering questions, deep cloning machine learning can breed new knowledge from the content it learned as shown on the right. This is logic resolution using existing knowledge to produce possible new knowledge using the ontological connections. Obviously, breeding new knowledge is one of the most exciting aspects of learning algorithms that are not as straight forward as it looks when using data-driven models such as deep learning. One of the advantages of knowledge-driven machine learning is that the “new knowledge” is transparent (can be verified by human inspection) whereas the same cannot be said for data-driven deep learning.

__________

This article is brought to you by exClone, a chatbot technology provider.

Chat with Vera about exClone.

Try free (no cc required) of our Cloning Platform via Linkedin access.

Join CHATBOTS group in linkedin.

You can follow exClone in Facebook, and in LinkedIn.

__________

#chatbot #chatbots #AI #artificialintelligence #ConversationalAI #Virtualassistants #bots #machinelearning #NLP #DL #deeplearning #deepcloning

Most Chatbots don’t Use AI, are Misrepresenting AI

3image

This title is the summary of what is happening in the market today, mostly encouraged by Facebook’s move for Messenger bots.

The ChatbotConf 2017 revealed this sad truth. There are 200,000 Messenger bots today, most likely none of them have a real AI backbone. A recent article summarizing the conference draws a similar conclusion.

End users of chatbots would not really care whether there is AI backbone or not if the chatbot they are using solves their problem. In a small fraction of cases, chatbots without AI can be helpful, especially in e-commerce transactions where buying and selling options are rudimentary, and the conversations can be buttonized. However, the AI issue surfaces when chatbots try to service higher complexity tasks. The way chatbots can be used in real life, this corresponds to, maybe, 90% of the cases. So, what is the AI backbone that is required?

The AI Backbone

Chatbots that represent AI must have some (if not all) of the capabilities listed below:

  • NLP: Capability to understand users’ responses in their most variant form.
  • Answering Questions: Ability to communicate with the user about a subject matter by absorbing knowledge and answering questions about it.
  • Asking Questions: Ability to ask questions to navigate the user to solve a problem.
  • Dialogue Behavior: Ability to engage users in certain behavior in concert with the chatbot’s objective (sales, transactions, advice, training, story telling, idea sharing, etc.)
  • Learning from Conversations: Ability to ask users for answers and to learn from them. This should be optional since social input may not be desirable for certain objectives.
  • Short-term Memory: Ability to remember the topic of conversation and interpret pronouns correctly. This requires chatbot to take into account what was said 2, 3, or 4 steps earlier.
  • Long-term Memory: Remembering previous chat sessions and starting conversation from where it was left of.
  • Emotions and Attitude: Ability to detect unproductive conversations, change strategy, or abort not to waste resources.
  • Awareness: Ability to self-assess its performance, produce reports about its performance, and suggest bot builders the weaknesses encountered.
  • Infinite Speech: Not to be restricted by a pre-defined steps of conversation.

Canning Responses Instance-by-Instance is not AI

Most chatbot platforms today are requiring instance-by-instance input from its builder to develop every step of the intended conversation in a rigid sequence. This approach is feasible for banking transactions, travel bookings, or other similar interactions where dialogue is restricted to solid options. Obviously, there is no AI backbone needed for such chatbots.

Chatbot science is at its infancy while most developers are expecting adult behavior.

Deep Learning is not a Silver Bullet

One of the latest misconceptions emerged in the market is that if there is enough data thrown at deep learning system, all the requirements listed above as AI backbone can be satisfied. Deep learning can only handle some parts of the required list, and the rest must be called the “chatbot science”. The only way to produce a chatbot development platform in the scope of AI backbone is to offer data-driven tools and/or knowledge-driven tools with certain level of built-in functions, where those functions define the secrets of the chatbot science.

——- FOLLOW OUR LAB ———-

Talk to Vera, exclone’s company representitive.

For exClone’s Chatbot Platform, click here for free trial via LinkedIn access.

Join our CHATBOTS linkedin group

Follow exClone in Linkedin or on Facebook

#chatbot #chatbots #AI #artificialintelligence #ConversationalAI #Virtualassistants #bots #machinelearning #NLP #DL #deeplearning

Cloning Chatbots for Education

linc3

In this context, cloning is an advanced form of impersonating where the chatbot can talk about the person’s life experiences and his/her expertise as curated by the chatbot maker. Compared to impersonating a person just using his/her image and name, cloning is obviously more involved and more challenging. As an example, you can chat with Abraham Lincoln and see how it was developed via one-shot machine learning technology with no-coding requirement. This chatbot uses Wikipedia content as its main source of conversation.

As one can easily deduce, all historical characters can be cloned into chatbots for educational purposes. But cloning goes beyond that as it allows creating chatbots of teachers themselves.

Top 6 Reasons Why Cloning Chatbots are Inevitable Tools for Education

  1. Control: Interactive content gives students much more control over what they want to focus on.
  2. Fun: Talking/messaging/chatting is always more fun than just reading.
  3. Ease: Use of small screen devices are ideal fit for chatbots which add to their educational role.
  4. New Teaching Methods: Chatbots can be a great summarization tool offering students main points to remember and option to dive deeper. Various new teaching strategies can be implemented.
  5. Creativity: Creation of chatbots can also be an educational experience.
  6. Feedback: Conversational analytics obtainable from chatbot interactions provide valuable clues to teachers as to how students learn, or fail to learn.

Profiliration of Chatbots Require Editorial Platforms

For chatbots to take a serious role in education, their development and profiliration must be fast and effective. Here are the three most important requirements for such a progress:

  1. No Coding: Chatbot creation should migrate from a coding effort to an editorial effort. This will enable students and teachers to develop education chatbots by curating content only.
  2. No Corpus Training: Underlying technology should not require large corpus training, and no experience in AI. One-shot machine learning techniques must drive these platforms processing the content for chat interaction while working silently in the background.
  3. Effective Communicator: Chatbots created for education must be effective, being able to answer improptu questions and offer topics of discussion. Although no chatbot today is expected to match human level dialogue, the educational effectiveness can be achieved by presenting chatbots for the specific goals they are designed for.

If you come across cloning/impersonating chatbots, please drop a note below. We may create a list of educational chatbots here.

How I made Abraham Lincoln CHATBOT in Less Than 10 Minutes

abe3

In our quest for turning static knowledge (documents) into interactive knowledge (chatbots) via the chatbot Platform, we have experimented creating a chatbot from scratch to completion. The main question was, how long would it take? We first downloaded Lincoln’s content from Wikipedia (16,000+ words), cleaned the content, made editorial changes, and curated some images. Then, it took less than 10 minutes to create a fully functional chatbot through the platform. Its one-shot machine learning technology (learning by reading) took less than 1 minute, and the previous 9 minutes were spent on entering the content into the platform. You can test this chatbot at this link and examine how it was developed.

It is a fully functional chatbot with short-term memory, answering impromptu questions any time, topical suggestions, detecting user behavior, and providing infinite speech. Its knowledge is limited to what the historians said as compiled in the Wikipedia page.

WHY IS THIS IMPORTANT?

For chatbots to spread and flourish in the future depends on how quickly they can be developed. This would mean development by editorial effort rather than by coding effort. In other words, chatbot platforms should only require content curation and selecting dialogue features. Everything else should be automated underneath (invisible to the developer), including machine learning and NLP capabilities.

Developers of chatbots in the future will be the writers not the computer programmers.

Current platforms offered by big companies (Microsoft Bot Framework, IBM-Watson, Amazon-Lex, Google API, and Facebook Messenger Platform) all require coding skills and/or AI experience. Obviously, developing the same chatbot for Abraham Lincoln would take much longer than 10 minutes when hands-on AI skills and coding are involved.

Considering the document stockpiles of enterprises, a quick and easy conversion to chatbots can be valuable for training, help desk, and other vital operations.

EDUCATIONAL CHATBOTS ARE HERE

The second reason for this initiative was to assess the value proposition of chatbots for the education sector. Here are the top 6 reasons why chatbots (conversational AI) will be inevitable tools for education:

  1. Control: Interactive content gives students much more control over what they want to focus on.
  2. Fun: Talking/messaging/chatting is always more fun than just reading.
  3. Ease: Use of small screen devices are ideal fit for chatbots which add to their educational role.
  4. New Teaching Methods: Chatbots can be a great summarization tool offering students main points to remember and option to dive deeper. Various new teaching strategies can be implemented.
  5. Creativity: Creation of chatbots can also be an educational experience.
  6. Feedback: Conversational analytics obtainable from chatbot interactions provide valuable clues to teachers as to how students learn, or fail to learn.

There is no doubt that one of the most active areas of conversational AI will be education. We will report how Abraham Lincoln chatbot was received in a follow up article.

——- FOLLOW US ———-

For exClone’s Chatbot Platform, click here for free trial via LinkedIn access.

Join our CHATBOTS linkedin group

Follow exClone in Linkedin or on Facebook

Is DIGITAL EMPLOYEE the Next Big Thing?

digitalemployee_small

All the technical jargon you have been hearing nowadays such as deep learning, artificial intelligence, natural language processing, etc., all converge to one single question for businesses: Can we build digital employees?

One may wonder what makes a digital employee different than all the software tools we are already using today. A digital employee may be defined as a computerized system that has superb communication skills using natural languages, and has some level of autonomy to make its own judgement and decisions.

Digital Employee represents the fine line where we delegate business responsibilities to autonomous systems, and where we communicate with them like talking to human employees.

WHAT WILL DIGITAL EMPLOYEES CONTRIBUTE TO?

Digital employees will directly contribute to business efficiency in 4 major areas as shown below. The communication at the top is essential for all other functions to perform cohesively. In other words, a digital employee starts from the core capability of communication and performing a high level dialogue.

de8

HOW DO WE BUILD THEM?

Creation of a digital employee cannot be a scientific project. Otherwise, it will remain very limited to a few examples based on substantial R&D budgets. This revolution will only happen when we have platforms that allow the creation of digital employees easily and fast. Here are the some of the top requirements for such transition:

de9

It is also important to mention that seamless integration to all communication platforms and operating systems is another key requirement.

SCIENTIFIC DISCIPLINES MUST COME TOGETHER

Creating digital employees through a platform will require many scientific disciplines and methods to amalgamate. There is no “silver bullet” solution to create such a complicated system. Below is a simplified landscape of disciplines that are most likely to contribute at least one aspect of development.

de7

The success will depend on who has the best cocktail of methods tucked under the platform which are literally invisible to the end user (i.e., the creator of digital employees).

BUSINESS INCENTIVES

Undoubtedly, there are several benefits of gaining digital employees as outlined below. However, their limitations compared to human employees (in certain aspects) represent a tradeoff. This trade off will exist until the technology reaches human level cognition, which may take a very long time.

de10

REVOLUTION TIMELINE

Estimating the timeline of the transformation from human information workers to digital employees is not an easy guess. Many businesses have adopted the IKEA model of DIY software during the last few decades, delegating tasks to clients. Banking is a prime example where you are supposed to use software to do transactions on your own. However, the current trend shows demand for command driven banking using conversational interfaces for requests like “Transfer $5,000 from checking to saving by tomorrow morning.” If we can talk to a digital employee, why bother using a software. And that’s the underlying promise for the upcoming revolution.

DIY Software model is wearing off, creating a future demand for digital employees.
We predict that the first solid evidence of this revolution will show itself by the fading away of DIY systems from our lives (including IKEA).

Creating a Business Entirely from Digital Workers (Expert Chatbots)

digitalbusiness

We are not too far away from creating a completely digital business with a single human (the owner) setting it up. A recent Forbes article mentions the possibility of replacing managers in a futuristic tone encouraged by the advances in blockchain and IoT, A Harvard Business Review article introduces iCEO, a software that makes executive decisions. All these developments are taking us to this ultimate goal.

Autonomous Digital Business is a concept much closer to reality than chips in the brain, or self-driving cars on the streets.

Current businesses are already “digital” in so many aspects. Automated trading in stock market was a pioneering example of how buying and selling decisions can be delegated to smart computers, and they have been operating for a while now. If we can trust computers with stock trading, why not trust them with our business decisions for buying, selling, hiring, etc.?

Amazon, for example, might be rated 70% digital considering all its web operations and robotic warehouses. As conversational agents (chatbots) steadily penetrating into the CRM and sales operations, the percentage of digital business is increasing. But can it be all “digital” comprised of agents and expert chatbots? Can we delegate all decision making roles to computerized agents to run our businesses?

Expert Chatbots Making Decisions

Our current understanding of the chatbots is not sophisticated enough to make them run a business autonomously. However, “expert” chatbots are a different ball game. I had explained in an article earlier how they differ from conventional chatbots. In a nut shell, an expert chatbot communicates with humans plus makes decisions based on the expertise it has. At exClone, we have seeded the first steps of this vision.

In the short term, the following decisions can be expected to be made from AI agents/expert chatbots in the realm of digital business:

digitalbusiness1

This is a simplified view of all possible conversational decision systems applicable to businesses. In this simple model, the business owner would interact with an executive chatbot to control and manage her business.

digitalbusiness2

This picture depicts a digitalization scheme via AI in its most naive form, with a potential to signal what the future holds.

Barriers to Entry

The most important parameter in this transition is the ability to create expert chatbots easily without deploying expensive scientific projects. Here is the list of 10 requirements to win in this race:

1- No coding effort should be required.
2- Deployment should be fast (as opposed to lengthly training/learning procedures)
3- Data requirement should be limited to the content of the expertise (as opposed to vast amounts of training data to be collected)
4- Easy to fix and modify (as opposed to black box approaches that require re-training the system)
5- Building an expert chatbot must be an editorial effort, not much different than writing a blog post.
6- Builders of expert chatbots should be experts themselves without the involvement of developers or scientists.
7- Should be able to converse effectively, yield reasonable advice, and make sensible decisions.
8- Must have a certain level of awareness to be able to analyze its conversations and make deductions.
9- Must be able to learn from overall operation by evaluating its objective function.
10- It should be easily deployed in all communication channels/platforms ranging from SMS to Slack.

The winning development platform must address all the issues listed above. Most of the current platforms offered by big corporations (Microsoft, Google, IBM, Amazon, Facebook) do not meet half of these criteria, and are targeted solely to developers, not to business experts.

How will the Future of Business Look Like?

There are several measurements that apply to business valuation today such as the market cap, EBITA, gross revenue, number of employees, etc. But none of these conventional measurements indicate how close the company is to scaling upward. The rate of digitalization could be such a measurement to fill in this gap.

A new key measurement of company valuation in Wallstreet will be the “Rate of Digitalization” in the near future.

Consider Amazon again. Let’s imagine a rival, equal size, equal volume, but everything done by hand (human labor). Who would you invest in? Amazon or the rival? Knowing the degree of digitalization in Amazon, the natural choice would be her. This extreme hypothetical example emphasizes the value of this new parameter. Today, it is all blurred in the narrative interpretations of stock analysts.

Far into the future, it is fair to assume that Fortune 500 list will start to include businesses entirely digital (automated) with few human owners or controllers.

A New AI System Writing Its Own Code to Produce Chatbots

topa2

If you heard AI systems that write their own computer codes, here is an example from exClone. The exclone’s platform is capable of taking any text, turn it into a special code (called CHATMATRIX), then spit out a chatbot that represents the content in a dialogue style. All in single step, with a push of a button.

The content is to be entered by subject matter experts in any particular topic. Hence the platform is called the Cloning Platform implying “digital cloning” of expertise. And the expertise can be anything, as simple as how to build a kite as long as it is articulated well. In this single step process, no coding is required to produce a chatbot.

The chatbots produced with this system have two primary functions: (1) Provide answers through presentations like how an expert would do by navigation options, (2) Provide answers to impromptu questions at any time during the conversation. There are bunch of secondary functions that make the whole experience human-like.

Machine Learning Similar to Human Learning

The human brain learns new knowledge while reading. As we all know, this process is very quick. The way to test learning is whether the person can answer questions about the sentences she/he read. exClone’s machine learning (ML) process works with the same principle, reading content and being able to answer questions. The automated step of creating a code for a given content is the byproduct of this machine learning process.

The editorial effort to create a chatbot involves few other choices by the expert. Some of these options include dialogue behavior (templates) that implement different objectives such as sales, help desk, advice, onboarding, surveying, etc. If you would like to experience the Cloning Platform, click here for free trial.

CHATMATRIX: A New Programming Language for Chatbots
Although the ML process creates a code for a given content (and template), the developers have a choice to add advanced functions and behaviors by further coding using the CHATMATRIX language. Bypassing the automation step, an entirely new chatbot can also be created. This high level language has the following features:

  • The language is comprised of predefined NLP functions for detecting user’s comments and predefined ML functions to generate response to the user.
  • Each statement handles not only the current exchange, but also the conversations took place N steps back. This enables strategizing the chatbot’s response based on history.
  • Each statement evaluates the availability of all possible response options, then chose the best one.

If you would like to learn more about CHATMATRIX, please drop a note below in the comment section.

Detecting Emotions is Key to Chatbot Performance

One of the advantages of CHATMATRIX is its ability to detect sentiments in user responses which leads to formulating emotions based on the short history of the conversation. Emotions are detected by the density of the sentiments during the conversational steps. This may seem like a humanizing effect of the chatbot experience, which is true in one sense. However, emotions are very useful for business purposes because it becomes a tool to filter out genuine users (sales leads for example) from people with no intention to engage in business.

Detecting emotions like satisfaction, confusion, boredom, curiosity, and anger allows strategic moves in dialogue flow. If the user is satisfied, chatbot can offer more options, or ask user’s contact information. If the user is confused, chatbot can ask the source of confusion. Many different strategies can be implemented based on the objective. Finally, conversation logs with emotion markers provides highly insightful information about the clientele.

————–

Join our CHATBOTS linkedin group

Follow exClone in Linkedin or on Facebook

Cloning Platform, click here for free trial.

For CHATMATRIX inquiries, drop a message.

DIGITAL CLONING: How Expertise can be Commoditized by AI Driven Chatbots

dc5-small

Biological cloning may be an immortal way to pass on our individual genetic information, but in digital form it offers something quite different: A new robotic society of expert chatbots as a part of our new digital life. Before digging deeper, let’s define what it is.

Digital Cloning is the duplication of a cognitive function based on the duplication of its source data (knowledge). Only duplicating data (text, image, video, sound, etc.) is not cloning just as how duplicating only DNA would not be cloning in biology.

Digital Cloning of Expertise is duplicating some particular expert knowledge along with its delivery mechanism, in this case a chatbot. In order to satisfy the criteria of digital cloning, such a chatbot is required to present expert knowledge in a useful way as well as answering related questions at a reasonable rate. Note that we are talking about “expert” chatbots here but not transactional chatbots where they book your flight or arrange your calendars. The difference between expert chatbots and transactional chatbots was explained in one of my earlier articles.

Digital cloning this way also includes persona, personal emphasis and choices since no two experts in the same field are the same. Personal variation is what makes combined expertise very powerful, always surpassing an individual expert’s opinion. Personal choices also reflect how expert content is curated to be cloned by its designer.

Expertise is the Most Valuable Commodity if it can be Shared
Expertise can be anything. It can be as simple as how to build a kite, or as complicated as how to perform a brain surgery. We all have some kind of expertise, some ideas, some vision, and stories to tell. In the enterprise world, expert knowledge is even more valuable since it is the driving force of business success. But expertise is only valuable if it is actionable. For that, expertise must be alive, always available, easy to share, easy to be consumed.

In today’s world, knowledge is shared in static (dead) forms of delivery methods: publications. Regardless of where they are published, and how long they buzzed or viewed, their destiny is ARCHIVES, which is a digital wasteland.

In Today’s World, Knowledge and Expertise Fade Away like Ocean Waves Breaking on a Beach and Retreating Back

This process resembles to ocean waves breaking on a beach (published), then retreating back (archived). They are at the mercy of Google’s ability to bring them to search queries. Worse than that, if such publications are within an enterprise environment where even Google cannot help you, their shelf-life will be even shorter comparable to how long the promoting emails are kept relevant, or how well you can query a database.

Accordingly, intellectual efforts made on a regular basis have no safe harbor to remain alive using our current digital systems other than being deposited somewhere (online or offline) including posting on social media, blogs, websites or corporate networks. You would agree with this point better when you catch yourself smiling upon discovering an old document on your computer with full of great ideas.

Immortalizing Ideas, Visions, Experiences, and Expertise
One way to keep one’s expert knowledge alive is digital cloning via chatbots. This must be a very simple process at the level of editorial effort not much different than blog writing. If it gets any more complicated than that, the demographics of digital cloning will be quite limited, and the anticipated affect will not emerge.

Digital cloning via expert chatbots is a new form of digital presence. Unlike the existing forms of digital presence such as facebook page, twitter account, or personal blog, an expert chatbot can maintain all your expert knowledge equally shareable regardless of when they were entered into the system. Every time you add some valuable knowledge, it enriches your chatbot’s response capability. People chatting with your chatbot would be presented your expertise, and would get answers to their questions. In addition, conversation logs can provide ultimate transparency to people’s concerns, curiosities, and demands relevant to the expertise served.

Community of Expert Chatbots in an Enterprise
Digital cloning concept offers tremendous advantages for enterprises in applications including, but not limited to, training, employee assistance, sales agents, help desk, and many other similar knowledge rich tasks. Managers and workers can clone themselves to offer an alternative communication channel within a company for all sorts of purposes. Expert chatbots can be created using databases and data silos for deep content (big data), converting such data driven systems into conversational experts. With such a transformation, we can start to assess the value of companies by their commoditization capability of expertise internally as well as externally.

A Society of Digitally Cloned Chatbots

Expert chatbots can refer to each other even for the same subject matter expertise very similar to how we use links in documents. This allows users to switch from one chatbot to another without a need for external search. Collaboration between chatbots in this manner will be the corner stone of the emergence of a robotic society in the mirror image of ourselves. Not to mention, a certain level of competition will emerge among the clones measured by who is the most popular expert chatbot based on number of referrals.

The emergence of such an ecosystem would redefine how we interact with computers, and would change our role from being sole digital workers to being part-time human parents of digital clones.

Such a transformation will also challenge the immortality arguments since biological death would no longer be 100% loss of one’s expertise and persona. One thing is for sure, all these possibilities are not a science fiction story any more, they are all here around the corner.

You can read my other articles on linkedin if you are patient enough to dig through, or you can wait until I clone myself (which I am in the process of doing it) and talk to my expert chatbot. You may even be able to hear my voice! Until then, stay tuned and join our CHATBOTS Group on Linkedin.

exClone Partners with Maana: How to Turn Data into Knowledge, then Talk to it via Chatbots

Image14

We are proud to announce a new partnership with MAANA, a pioneering tech company that turns data into actionable knowledge to accelarate enterprise profitability. The objective of this collaboration is to add a communication option where the users of the knowledge platform interact with the system via the most casual, natural, and untrained conversations. The vision of bringing  knowledge/data assistants into operational workflows is remarkable from the stand point of industrial artificial intelligence (AI).

In this article, we will share a simplified description of the problem at hand, and the path to its solution in its most general manner. The modes of conversation presented at the bottom of the article are self-descriptive value propositions as to how access to knowledge can be accelerated.

Before I do that let me briefly explain what Maana knowledge platform does and how exClone technology works with it.

The Maana Knowledge Platform is used by the largest Fortune 500 companies in the world and is uniquely designed to enable subject-matter experts to quickly build hundreds of interconnected models that encode the expertise of subject-matter experts combined with data from across silos in the context of optimizing an asset or workflow. These knowledge models provide continuous, actionable recommendations into the operations of assets and workflows enabling faster and better daily decisions by thousands of employees that result in increased enterprise profitability.

What can Chatbot Communication bring to the table?

In its most simplified strawman drawing, turning data into knowledge requires handling of 5 technical problems collectively. Going from bottom to top, they are (1) data silos and data lakes, (2) integration, (3) analysis, (4) retrieval, and (5) communication.

Image10

At the top layer, communication function must allow the users interact with the system in the most casual, natural, and untrained manner. That’s where chatbots play an important role as being a part of the last ring of the chain.

You might as well consider chatbot as a waitress/waiter in a restaurant. Despite the massive operation in the kitchen and abundance of meal options, the only interface you would have with this system would be her/him. A typical customer – waitress interaction lays out all possible combinations that a chatbot must handle.

  • Going over the menu: A typical and most common interaction where the customer is presented options to chose from and the questions about the options are answered.
  • Questions without the menu: An interaction where customer choses to investigate options without looking at the menu, and such questions must be answered impromptu which may sometimes lead to a menu item.
  • Specials: An introductory style of interaction where the waitress takes an active step to assist the customer about the best options for that particular moment in time before any conversation starts.
  • Remembering the customer: An interaction with a known customer where previously used options are brought up, and the customer is alerted to the variations from the previous state of affairs.

These 4 types of interactions are the range of information service applicable to all chatbot applications. Bringing these on the table of knowledge platform, however, has some unique challenges.

How Does a Chatbot Serve Knowledge Platforms?

There are 5 main functions of a chatbot to bridge the gap between the end-user and a knowledge platform as shown in the simplified diagram below.

Image12

  • Interface: Chatbot interfaces are usually simple and SMS like, which are enriched with image and video insertions. They are particularly popular for their advantages in the ever growing mobile device usage. No special requirements would apply to interface design that could be attributable to the knowledge platform.
  • Decision: This is the state information of the ongoing conversation where the system (1) qualifies if the user’s response needs to be sent to the knowledge platform, (2) if there are options to present for navigating to the next level, (3) if the current response is the continuation of the previous response via short-term memory, (4) if the user must be helped according to his/her historical choices, and (5) if the user’s response is related to the answers in the short-term memory. This list is actually much larger with details that belong to the type of application and nature of the knowledge operation.
  • Translation: This step translates a qualified English sentence (qualified by the Decision step) to a system specific retrieval command(s) within the knowledge platform. This translation requires ontological parsing of the English sentence then formation of it in the new language.
  • Generation: Once the result is retrieved, it has to be put into an English sentence for better communication. This seemingly simple task can actually be quite challenging, and is also known as the generation problem in computational linguistics. Bite-size information is a concept that has to be decided for the generation step according to the objective of the chatbot. For example, if the chatbot is helping with federal regulations, then the bite-size information can be a full sentence, or sometimes a paragraph, of unedited original text, with very little generation challenge. However, with numerical data, diagrams, tables, images, or video, the bite-size determination can be a difficult task.
  • Navigation: This step requires an independent cycle of communication with the knowledge platform to harvest available options of navigation. Usually, the options within the knowledge domain are mirrored at the chatbot level so that the users can access knowledge with less effort.

Modes of Conversation

There are various modes of conversations that a chatbot can conduct, making this interaction much more valuable than using a static, single-step search box. Here are some of these possibilities using a hypothetical content.

bigdata13

Case A above shows an impromptu answer (4,788 tons) presented with the generation capability. Case B and C show how chatbots can utilize their short-term memory to suggest alternatives and navigation options while remembering important aspects of the original query that was asked 2, 3, and sometimes 4 steps earlier. While the knowledge platform was utilized in A, the responses B and C may come from the chatbot itself depending on the availability of embedded (learned) content. Also note that the clickable options are very useful especially when the chatbot is used on a mobile device.

bigdata15

Case D shows a possible exchange to narrow down the type of analysis available in the knowledge platform domain before it has been retrieved. Case E illustrates long-term memory to continue the previous conversation which can eliminate unnecessary steps to reach back to the same point. Case F shows that knowledge platform and chatbot can create alerts to indicate updates in the back end.

These are some of the possible exchanges that could be achieved from chatbot – knowledge platform combination.

 

 

 

 

 

 

 

 

 

 

 

 

The Thick Blue Line Between Chatbots

Image28
Since the recent upsurge of chatbots, a lot of confusion has surfaced about chatbots in general. Similar to the emergence of laser technology when no one was quite sure whether we were entering the star wars era with military satellites shooting each other using laser guns, some people mistakenly expect that the chatbot technology can deliver results close to the fantasies portrayed in Hollywood movies. To make things more explicable, we first need this basic distinction: Transactional chatbots versus expert chatbots.

TRANSACTIONAL Chatbot is a simple interactive system delivered in a dialogue style interface where the main objective can be as simple as organizing calendars, booking reservations, helping check-out process, or presenting retail options.

EXPERT Chatbot is a sophisticated conversational system that actually engages in a dialogue with the user about the expert knowledge it embodies. The objectives are more ambitious such as help desk, tech support, employee assistant, or online advisory systems.

The Difference
The blue line in between these two categories of chatbots is actually not thin, if not very thick. The thickness comes from the scientific and technological challenges involved comparing one to another.

Transactional chatbots operate in a single dimension: Natural Language Processing (NLP). Using NLP, whatever the user says (or types) is to be detected in order to perform some form of transactional response. If the chatbot is designed to operate for a specific task, the sphere of language detection is nicely confined within a narrow band. As a result, some basic NLP technology would be enough to power these chatbots as long as the users’ dialogue do not diverge away from the chatbots main objective. Many messenger chatbots fall into this category, and some has real commercial future.
Image39

The situation with expert chatbots quickly gets much more complicated because they must operate at least in 2 dimensions. The second dimension, machine learning (ML), is needed to absorb content (expert knowledge) into the system. As shown in the diagram above, ML will also help the NLP capability (green line) with increased content and training. The problem here is that the conventional ML algorithms (like neural networks) are complicated, rely on data volume and quality, and are black-box approach. They are mainly an “engineering” approach to knowledge processing devoid of innovations in computational linguistics, semantics, and even in psychology. New approaches to ML are needed to fit this particular operation before expert chatbots can flourish.

Yet There is the 3rd Dimension
One of the largely misunderstood aspects of chatbots is the missing 3rd dimension: dialogue behavior. This 3rd dimension gives “life” to a chatbot which would otherwise act lifeless without any active speech or goal-oriented behavior.

Image399

To give you an example, if the purpose of the chatbot is to be a sales person, then it should have a salesmanship behavior. Behavior modeling is another untapped territory that involves disciplines as far away from engineering as it can be: psychology. Game-theoretic, behavioral algorithms can actually provide a framework for NLP and ML processes to fill in the dialogue engine with knowledge and language detection.

We, at exClone, are pioneering this combination using an umbrella term “digital cloning technology” that can be accessed via our Creators’ Platform coming out soon. The good news is that chatbot developers will not need any coding, or even experience in any of these disciplines. Although “advanced” options will be provided for those technical geniuses, the platform will aim enterprise clients who want to solve the problems of communication quality, scalability and cost across enterprise operations.

The Last Category: Purposeless Chatbots
I would originally call this group of chatbots as “useless chatbots” because they are. Unfortunately, there is an alarming rate of them being advertised (surprisingly) by the misguided PR departments of tech giants like IBM, Microsoft, Apple, and Google. Let me give you two examples, then you can fill the rest.

What is Siri? Apple adopted Siri, which could be a good move, but then deployed it without any clear “purpose” by hijacking an important button functionality. As a result, 9 out of 10 things you ask is not fulfilled by Siri. Siri does not ask you any question, it does not guide you to any specific problem solving. Why not deploy Siri with an actual purpose, even if the purpose is limited to, say organizing your calendar? A clear lack of vision (after Jobs) manifests itself by not even being a platform (unlike Amazon’s Echo), so that purposeful chatbots could have been launched from a Siri platform.

Another example is Microsoft’s Tay, now its derivative Zo. Using a pure engineering approach of machine learning, they are training the system using tweets to create a chatbot that has no clear purpose. What problem does it solve? If it is a social experiment, Zo will become an average teenager, with knowledge of teenager tweets, without any distinct behavior, and no contribution to society beyond chit chat engagement. Such projects will eventually come to a realization that knowledge representation, natural language, and human-like dialogue cannot be handled solely by an engineering approach, and such purposeless, “do-it-all” attempts will fall short.

Purposeless chatbots are destined to suffer from the lack of usefulness, and they will fail to fulfill a promise that has been advertised beyond reality. Although we are accustomed to see these companies shooting themselves in the foot, it is somewhat interesting to see that while they are promoting “learning” technology, they are failing to learn themselves not to hype the tech markets for short-term sensationalism.