NTENT Implements Applied Data Science to Identify User Intention and Increase Relevance

NEW YORK--()--NTENT announced today a multiphase approach to understanding language that uses Applied Data Science to sift through data collected worldwide, as a means to measure user intention and provide relevant solutions.

Applied Data Science refers to the collection and collation of information derived from a blend of data mining, data processing, predictive analytics and machine learning. Through the union of computational theory and pattern recognition, machine learning allows software to independently identify, explain and evaluate fresh rules and behaviors, then respond in ways aligned with predictable human patterns. NTENT’s patented technology implements three main categories of Applied Data Science: Data Acquisition, Natural Language Processing (NLP) and Data Analytics.

In the Data Acquisition phase, NTENT collects content generated from user requests, usage data, and knowledge used in reasoning and language understanding, to help educate the NTENT Search Platform. Each component provides input to help our technology learn. Usage data can be used to support language models that help interpret word and concept frequency while knowledge assists the platform in word comprehension. Content chosen in response to a query offers valuable insight into a user’s intent. For example, a search for “cobbler recipe” would identify “cobbler” as a dessert rather than a person who makes shoes. Strong results may not even include the word “recipe” but may instead pull results that simply list ingredients and directions for a meal.

NTENT’s Natural Language Processing (NLP) engine generates computable, semantic representations derived from natural language, aggregated through various content, ranging in complexity from queries to chats, forum posts and more. These semantic representations serve as a neutral language that allows communication between multiple applications engaging with the NLP engine, enabling it to measure user search intent and market-specific relevance.

Data Analytics tracks and mimics system and product behavior by leveraging usage data and market analysis. The NLP engine is structured to cycle through several customized classifiers and scorers that yield signals to help calculate the most probable output scenarios. One such classifier is the Extended Named Entity Recognizer designed specifically to help the NLP engine differentiate proper names or polysemy, for words that sound or look the same but mean different things such as “bass fish” or “bass instrument.” These signals assist the Machine Learning module of the NLP engine to make more informed decisions. This process known as Ambiguity Resolution through the use of semantic ranking was unveiled by NTENT this past May.

“Applied Data Science at NTENT covers a wide range of projects with teams of core programmers, machine learning experts, language engineers and ontologists at the helm,” said Chief Technology Officer, Dr. Ricardo Baeza-Yates. “NTENT can take on complex data science problems because we have developed a rare symbiosis between in-house and state-of-the-art data analytic components. Years of meticulous engineering, evaluation and deployment have allowed us to hone our product without impeding its core purpose.”

About NTENT: NTENT™ sits at the crossroads of semantic search and natural language processing technologies. Our patented, proprietary technology powers our comprehensive platform that transforms structured and unstructured data into relevant and actionable insights. This level of intelligence enables us to predict and deliver relevant information based on user intention. Learn more about NTENT at http://www.ntent.com.

Contacts

NTENT
Kerstin Recker
Head of Marketing
krecker@ntent.com

Contacts

NTENT
Kerstin Recker
Head of Marketing
krecker@ntent.com