Lexalytics Announces Text Analytics Suite Availability for Any Computing Environment  

Feb 14, 2019

Lexalytics, a provider of “words-first” machine learning and artificial intelligence, announced that its entire text analytics and natural language processing (NLP) product suite is available for deployment in any computing environment—on premises; private, public or hybrid cloud; or individual workstation. Previously, the only on-premises option from Lexalytics was its core Salience text analytics libraries which are integrated into existing customer or BI applications. Now, Semantria, the company’s text analytics RESTful API, as well as Lexalytics Intelligence Platform, a complete application for gathering, processing, modeling, analyzing, and visualizing relevant information extracted from unstructured text, can also be deployed on premises, in addition to a public or private-public cloud, hybrid configuration. 

Lexalytics also announced it is pioneering a new machine learning approach to text analytics that it is calling “micromodels.” In any text analytics application, there is generally a small subset of phrases, concepts, and entities that are difficult to correctly score or extract with monolithic “macromodels.”  These ambiguous terms can cause a drop in the system’s accuracy. For example, the word “tight” can mean many things in standard and vernacular English, from “strongly fixed,” such as, “The lid is tight,” to “cool,” as in, “That video was tight!” and can have positive, negative, or neutral sentiment, depending on usage.  

Text analytics companies have traditionally approached this problem by training one monolithic model with large amounts of data. With micromodels, Lexalytics can greatly improve accuracy by identifying the critical subset of terms unique to a particular customer or industry and creating micromodels for each term, dramatically reducing the amount of data and hours required to train the system. Lexalytics predicts that micromodels will approach 100 percent accuracy for certain words and phrases, beating a human’s comprehension and other systems currently in use.  

Related Articles

AnyClip addresses another major publisher pain point by eliminating operating costs associated with video.
Ignite Social Media, the original social media agency, announced a new content planning and media buying approach called Content That Converts.
Expands testing capabilities to ensure device-level conformance with the General Data Protection Regulation (GDPR) framework for companies worldwide.