BLOOMINGTON, Ind., Oct. 22, 2019 (GLOBE NEWSWIRE) — Megaputer Intelligence, Inc. will share an innovative new tool for building training datasets for use in machine learning during a presentation at the Text Analytics Forum ’19 held in Washington, DC on November 7.
Dr. Sergei Ananyan, CEO of Megaputer Intelligence, Inc., will present a cutting-edge topic entitled, “NLP & Rule-Based Approach for Fact Extraction: Launchpad for Machine Learning Techniques” on Thursday, November 7 at 11:15 AM EST. The Text Analytics Forum will host the presentation at the JW Marriott in Washington, DC as part of its comprehensive programming, running from Nov 4-7.
The content of the presentation is designed for people interested in discovering how to achieve higher accuracy from machine learning, relieve the burden of needing experts to manually create a gold standard training dataset, and illuminate the black box surrounding machine learning as much as possible with insight into today’s latest technological advances. Professionals such as text analysts, data scientists, DBAs, information knowledge architects, knowledge organizers, taxonomists, ontologists, CIOs, CKOs, research scientists, and data quality managers will benefit greatly from this technique to overcome well-known challenges of machine learning.
One fundamental obstacle for using machine learning (ML) to accurately extract facts from free-text documents is that it requires huge quantities of pre-categorized data for training a model. Manual annotation is not a viable option in most cases, as it would entail enormous commitments of time by human analysts. Dr. Ananyan will outline a rule-based approach for the automated generation of pre-categorized data that can be further used for training ML models. This approach relies on writing queries expressed in the powerful Pattern Definition Language, which fully leverages the results of underlying natural language processing (NLP): the syntactic, morphological, and semantic analysis of documents. The sequential application of rule-based and ML techniques facilitates the high accuracy of results.
Beginning on November 4, and leading up to the day of the presentation, Dr. Ananyan will be near booth #409 within the Enterprise Solutions Showcase to discuss how to build training data more effectively. Megaputer Intelligence is a gold sponsor of this year’s KMWorld event and will showcase a number of advanced text analytics solutions for pharmaceutical, insurance, finance, manufacturing, healthcare, and other industries.
About Text Analytics Forum
The Text Analytics Forum (www.text-analytics-forum.com/2019/) is a co-located event with KMWorld, Taxonomy Boot Camp, Office 365 Symposium, Enterprise Search & Discovery, and Complexity in Human Systems Symposium. The Forum has something for everyone: whether you are new to the field and want to understand how text analytics can add new capabilities or you are an experienced text analyst and want to see what the latest techniques and tools can add to your repertoire.
Megaputer Intelligence (www.megaputer.com) is a leading provider of data and text mining software and custom analytical solutions for various application domains. Megaputer analytical tools enable customers worldwide to make informed data-driven decisions. Megaputer is a registered trademark of Megaputer Intelligence Inc. in the United States and/or other countries. The names of other companies and products mentioned herein may be the trademarks of their respective owners.
For more information:
Credit: Google News