Job Description Individual should have good knowledge on Machine Learning and Statistical NLP techniques . The role requires : Content Enrichment for cognitive intelligence for enterprise wide automation platform(s) Focus on existing text and data mining processes Ability to work with varied group to develop new extraction methods and extract information relevant for new product development Good understanding of concept indexing or annotation (for example using ontologies in the medical domain), relationship extraction (for example in disease pathways) or extracting data from images and tables.
Write design specifications, unit tests, maintaining documentation and perform code reviews.
Text and Data Mining : Use ML techniques to work on historic structured / unstructured data to implement automated indexing and annotation processes.
Improve data excerption processes across organization. Contribute to the content strategy : Identify and ingest new technical capabilities to forward Novartis mission of leading the way in reimagining medicine to improve and extend people’s lives.
Data analytics to support businesses and products : Identify research trends / drive decision for content acquisition strategy / use visualizations tools to present the extracted data for the leadership team and key stakeholders Serve as internal specialist on data extraction and NLP matters : Build a culture of product and process innovation Minimum requirements University graduate (Master of PhD level) computer science, computational linguistics or an associated area from premier institutes.
Fluency in written and spoken English At least 5 years’ experience working in Natural Language Processing (NLP) especially in entity extraction, word-
sense disambiguation, information clustering and data mining. Experience with internationalization, validation techniques, and using statistical techniques in decision making.
Good exposure in C / C++, PHP / Lua and Perl / Python / Java , SQL queries, *nix systems, open source software and libraries.
Familiarity with taxonomy applications across scientific and healthcare disciplines is a plus. Good communication and documentations skills with the ability to convey complex technical concepts to non-technical professionals.