Lexalytics Extends Text Analytics for the Enterprise with Machine Learning Capabilities
Lexalytics, a provider of cloud and on-premises text analytics solutions, has made improvements to the machine learning (ML) capabilities of its Salience text analytics platform to make it easier for data analysts and scientists to train their Salience software.
The latest release of Salience, 6.2, also enables professionals in social media marketing, voice of the customer (VOC), voice of the employee (VOE), and customer experience management (CEM) to more accurately analyze email communications, as well as text that includes the latest emojis.
With this release, Lexalytics is substantially bolstering its ML capabilities, said Jeff Catlin, CEO, Lexalytics, making it easier for customers to teach and “tune” the software to meet their needs, and expanding the capabilities of what text analytics and NLP can accomplish.
Key new features of Salience 6.2 include HSDTrainer, a new tool to “train” sentiment analysis, combining the training of a simplistic machine learning (ML) system with Lexalytics’ natural language processing (NLP) technology. The Lexalytics HSDTrainer can consume any text that has been appropriately marked up for sentiment, and then return a list of phrases and suggested scores for that text, allowing analysts to train sentiment.
Moreover, with Salience 6.2, social marketers can now analyze the meaning and sentiment of content that includes the latest emojis released in Unicode 9.0. The 6.2 release also adds the ability to ingest email databases, stripping out headers and footers, eliminating duplicate emails and analyzing email threads. And, for improved named entity recognition, Salience 6.2 combines Lexalytics’ machine learning models and known lists of people, places and things (entities) to improve precision and recall scores, known as F1 scores, by up to 25%. In particular, the company says, due to its growth in Asian markets, including China, Japan and Korea, the company has focused on improving Salience's ability to more readily recognize people’s names from those regions, as well.
Lexalytics’ on-premise text analytics engine processes billions of documents per day, and is used by seven of the top 10 social monitoring and social marketing providers, as well as leaders in customer experience management, survey analysis and business intelligence software, according to the vendor.