Machine learning has become a core technology underlying many modern applications, especially utilizing natural language processing, where the techniques provide powerful methods for analyzing large data sets, such as contracts, electronic health records, social interactions, and other unstructured text data. With the ability for recent powerful techniques to retain meaning, search, and perform machine translation at high fidelity, alongside many open-source traditional and hybrid methods, transforming unstructured content to structured insights, events, and relationships is at the fingertips. Organizations are looking to leverage these emerging technologies and close capability gaps to ingest, monitor, error-check, automate, or improve their capabilities in processing and understanding hundreds of millions of documents. While certain tasks are well addressed by existing systems, organizations often still struggle with implementation, identification of the correct methods & algorithms, as well as properly scale their models to solve open challenges within their terminology. In this session, we examine the data strategy and technical use cases involving natural language processing, the algorithms appropriate for certain project objectives, and discuss the development and deployment of these solutions.
Overview and Author Bio
Developing Natural Language Processing Pipelines for Industry
Michael Luk, PhD
Chief Technology Officer | SFL Scientific