Jul

nmodes Technology - Overview

                                                       

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.

Interested in reading more? Check out our other blogs:

Abundance of Information Often is a Liability

A massive change has occurred in the world during the last ten to twenty years. Until recently and throughout the history of mankind information was hard to access. Obtaining and sharing information was either a laborious process or impossible, and the underlying assumption was that information can never be enough.

Today, of course, we have the opposite picture. Not only information is easily available, it keeps pouring in from a growing number of sources, and we continuously find ourselves in situations when there is more information than we want or able to process.

A major task we, as species, are facing is therefore how to reduce or filter out relevant information. It is, to repeat, in direct opposition to the task we’ve been accustomed to during all previous centuries, which was how to obtain information.

Since this change took place only recently, within a lifetime of one generation, we didn’t have time to develop efficient set of procedures to address the new problem. But the work has started and will only accelerate with time.

READ MORE

Beware the lure of crowdsourced data

Crowdsourced data can often be inconsistent, messy or downright wrong 

We all like something for nothing, that’s why open source software is so popular. (It’s also why the Pirate  Bay exists). But sometimes things that seem too good to be true are just that. 

Repustate is in the text analytics game which means we needs lots and lots of data to model certain  characteristics of written text. We need common words, grammar constructs, human-annotated corpora  of text etc. to make our various language models work as quickly and as well as they do. 

We recently embarked on the next phase of our text analytics adventure: semantic analysis. Semantic  analysis the process of taking arbitrary text and assigning meaning to the individual, relevant components.  For example, being able to identify “apple” as a fruit in the sentence “I went apple picking yesterday” but to  identify “Apple’ the company when saying “I can’t wait for the new Apple product announcement” (note:  even though I used title case for the latter example, casing should not matter)

READ MORE