Megaputer Presents Boost for Machine Learning at the Text Analytics Forum

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” at this year’s Text Analytics Forum.

One fundamental obstacle for using machine learning (ML) to accurately extract facts from free-text documents is that it requires huge amounts 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.

About the Presenter