The Automation Is Coming

nmodes ability to accurately deliver relevant messages and conversations to businesses is based on its ability to understand these messages and conversations. Once a system understands a sentence or text, it can easily perform a necessary action, i.e. bring a sentence about buying a car to the car dealership, or a complaint about purchased furniture to the customer service department of the furniture company.

Understanding sentences is called semantics. nmodes has developed a strong semantic technology that stand out in a number of ways.

Here is how nmodes technology is different:

1. Low computational power. We don’t use methods and algorithms deployed by almost everyone else in this space. The algorithms we are using allow us to achieve high level of accuracy while significantly reducing the computational power. Most accurate semantic systems, e.g. Google’s, or IBM’s, rely on supercomputers. By comparison our computational requirements are modest to the extreme, yet we successfully compete with these powerhouses in terms accuracy and quality of results.

2. Private data sources. We work extensively with Twitter and other social networks, yet at the same time we process enterprise data.  Working with private data sources means system should know details specific only to this particular data source. For example, when if a system handles web self-service solution for online electronics store it learns the names, prices, and other details of all products available at this store.  

3. User driven solution. Our system learns from user’s input. Which makes it extremely flexible and as granular as needed. It supports both generic topics, for example car purchasing, and conversations concentrating on specific type of car, or a model.

AI training is a critical part of conversational AI solutions, a part that makes AI software different from any kind of software previously created.
AI training is not coding.
Unlike all other existing software which is fully coded.

Let us consider a simple example:
We create chatbots for two companies, one company is selling shoes, another is selling cars. From the software standpoint it is one chatbot solution running as an online service accessed remotely or a program available locally. In both cases they are two identical instances of the same software (one instance for the shoes company, another for the cars company).
Yet, for the first company the chatbot is supposed to talk about flip-flops, summer shoes, high heels and so on. For the second company, however, the chatbot is not expected to know any of that. Instead, the chatbot should be able to support conversations about car brands, car models, should know how to tell Toyota Camry from Toyota Corolla, etc. This shoes and cars knowledge is not programmable. It is trainable. It is not coded, instead it is a part of language processing capability that AI solutions like chatbots have. And herein lies the major differentiation and advantage of the AI solutions compared to traditional software.

How to train AI?
There are several ways to do it. Sometimes AI system can train itself, improve its linguistic ability over time. It also can be trained by professional linguists. And in some cases, by the users. The latter is the desirable scenario because businesses know better than anybody else what they want their chatbot to talk about.
It is not easy, given the existing state of AI technology, and usually requires a high level of technical knowledge. You may have heard mentions of intents and entities in chatbot discussions. These are examples of linguistic elements AI training is currently based on.
Without proper understanding of what these linguistic elements are and how language acquisition process works in existing AI systems it is better to leave AI training to professional linguists.