Natural Language Interaction | Artificial Solutions

Natural Language Interaction

What’s Natural Language Interaction (NLI)?

What is Natural Language Interaction

Natural Language Interaction (NLI) enables people to interact with any connected devices using everyday words and phrases. NLI does this by adding intelligence to speech recognition.

While speech-enablement is not a new concept, existing solutions are quite restrictive in that users are typically limited to 2 or 3 word commands; there is no conversational flow based on the natural language that you would use if you were talking to another person. This offers a very poor user experience, because there is no intelligence in the interactions.

This is where Artificial Solutions steps in and takes the technology to the next level.  Our technology – Teneo – is powered by our sophisticated NLI engine in order to deliver intelligent conversations between consumers and the everyday devices they use.  Imagine having an intelligent virtual assistant on your Smartphone, Smart TV, SatNav, games console, laptop or tablet – not command based but able to hold two-way conversations using everyday language.

Much more than just voice activation, NLI enables mobiles, consumer devices and appliances to deliver a realistic, two-way experience that adds tangible and lasting value to the consumer.

Our NLI technology is device, platform and language independent and is typically implemented in three main ways:

  • Speech-enabling applications for Mobile Computing such as Smartphones and Tablets.
  • Speech-enabling applications for Connected Consumer Devices such as Smart TVs and SatNavs.
  • Delivering automated, online Virtual Assistants for customer service & sales and for internal help-desk solutions.

In addition, our clients get unprecedented customer understanding through our analytics & discovery tools.

Certainly our award winning technology is already widely acclaimed and used by enterprise customers globally.

 


Technology that understands you

Natural Language Interaction (NLI) uses powerful linguistic libraries and rules to enable consumers to talk to electronic devices in free-format, natural language conversations.

It is made commercially available through our award-winning Teneo Interaction Engine. NLI should not be confused with Automatic Speech Recognition (ASR) solutions which convert spoken words to text and is typically used for relatively simple applications such as keyword based voice interfaces. NLI utilizes ASR to ‘capture’ spoken word and then provides the ‘brain-power’ to analyze, reason and react to what is being said. You can learn more about the differences between NLI, TTS (Text To Speech) and ASR under the tab “NLI vs. ASR and TTS”.

NLI follows three key steps to process user input and react in an intelligent way.
Analyze, Reason and React

  1. Analyze: It first analyzes the user’s input – either spoken or in text – using a robust linguistic understanding library to understand and then derive the meaning (or potential meanings), from the input. At this stage, it eliminates ambiguity, for example, if a user asks about a ‘bank’ on a financial website, it knows that the user is referring to a financial institution and not a mound of earth!
  2. Reason: Advanced linguistic interpretation and business rules are used to simulate ‘intelligent thinking’, allowing it to reason like a human and determine the most appropriate way to react, taking into account contextual factors such as the day of the week, user location, information from previous dialogs and data about the user retrieved from back-office systems such as CRM systems.
  3. React: The last stage is to perform the necessary actions in the most appropriate manner. This may be to give a suitable verbal or textual response, to ask for more information, open a webpage, play a video, open another app, automatically fill in a form or execute a transaction by updating a database or integrating with one of your backend or e-commerce systems.

These three steps all happen seamlessly in milliseconds, with Teneo able to handle thousands of interactions simultaneously. But it doesn’t end here; there is a constant process of improvement. Teneo Insight gives unprecedented levels of insight and understanding and this knowledge is used to constantly update the knowledge of your solution.

Teneo Studio is used to make these updates. Teneo Studio is an intuitive, user friendly tool that allows non-technical, non-linguists to build intelligent, humanlike and capable NLI solutions and puts you, as project owner, in complete control of any updated responses and process flows.

The Teneo Interaction Engine is the ‘brains’ of our NLI technology; it receives user input (whether voice, text, gesture or other forms of input), analyzing reasoning and reacting, then responding in the most appropriate manner.  Teneo Insight constantly analyzes performance, identifies trends and provides insight that is used to further improve the performance of our NLI solutions.  Teneo Studio ensures updated and new knowledge and functionality is quickly added to the solution. This virtuous cycle constantly updates and improves on the overall solution.

This diagram illustrates this process:

Teneo Interaction Engine


More than commands

Natural Language Interaction makes it easy for your customers to interact with your mobile and connected consumer devices, with your apps and software and with your business in the manner that is best for them.

Natural Language Interaction offers:

  • Intelligence.  NLI understands you, not the other way round.
  • More than commands. NLI understands content, context and meaning
  • Bi-directionality.  You can have a meaningful conversation, not a series of one-way instructions.
  • Interactivity. NLI enables you to interact and converse, not just wait for the results of a task to be processed.
  • Goal-Driven Dialog. NLI can deliver responses based on turn-taking or goal-driven settings
  • Proactivity. NLI can proactively gather missing information, disambiguate responses or push information to the user.
  • More than search. NLI-powered solutions provide real, useful dialog, not just dumb searches.


Adding intelligence to Speech Recognition

Our Natural Language Interaction technology, delivered through our Teneo Platform, is so much more than a “voice recognition” or “automatic speech recognition” tool, though it can do that if you want. We like to say that our NLI technology adds true intelligence to voice commands.

Definitions:

  • Automatic Speech Recognition (ASR) – also known as computer speech recognition or speech to text – converts spoken words to text.
  • Text to Speech (TTS) – converts text to spoken words.

ASR vs. NLI:

Whilst ASR converts spoken words to text and is often used in applications such as voice dialing and dictation tools, it doesn’t have human-like intelligence. It can’t qualify a question by asking for more information. It can’t remember. It can’t search other information sources for information. In summary, it’s not able to deliver intelligent solutions.

However, with NLI technology such as Teneo, we are able to make a machine understand questions no matter how they are phrased. It also has the capability of remembering information and keeping it for later in a conversation.  So you can ask complex questions in free-format, natural language and Teneo will learn, reason, understand, and then apply this knowledge to act on what has been said.

For example, with ASR your Xbox game will understand “stop game”, but only that one command spoken in one specific way. With NLI implemented you could say “I want to stop” / “please, let’s quit” / “I don’t want to play anymore” / “this is boring, let’s do something else” and more,  and the program would understand all these inputs as meaning the same thing, asking further qualifying questions if necessary. NLI has added the intelligence which makes it possible for you to speak to your game console in exactly the same way you would talk to a person.

How ASR, NLI and TTS work together:

The Teneo platform supports spoken dialog with the use of ASR to handle speech as an input channel; and TTS to produce spoken output. The Teneo Interaction Engine handles the Natural Language Understanding (NLU) and Dialog Management in order to make the NLI solution understand, reason and react (as opposed to simply performing a voice search).

Artificial Solutions specializes in the complex field of artificial intelligence and natural language interaction and has chosen to partner with a range of providers that deliver speech technology. The Teneo Interaction Engine uses an API that links to ASR vendors to capture voice on the device and send it to the ASR engine to get a written output/suggestion back of what was most likely said. The ASR vendor can provide this service in the cloud or the ASR engine and the TTS engine can be hosted by Artificial Solutions.

The Teneo platform’s robustness in NLU and Dialog Management precisely fill the gaps left by ASR systems to create a truly natural experience, using a number of proven ASR-handling strategies to increase the quality and the end-user experience.  Combining the capabilities of the Teneo Natural Language Interaction platform with the capabilities of ASR systems leads to a superior user experience; a truly natural speech-based interaction between a human and a device.