Auto NLP: Pretrain, Tune & Deploy State-of-the-art Models Without Coding
How do we empower non-technical people to train NLP models and deploy them for solving tasks such as sentiment analysis, named entity recognition, and document classification? By abstracting away the implementation details and focusing on domain knowledge transfer, from experts to models, through simple annotations.
This talk demonstrates how John Snow Labs enables the complete workflow from defining a new model, reusing existing models to pre-annotate documents for a faster pace, active learning during annotation to continuously improve results, model evaluation, and finally model publishing. All you need to bring is the experts to learn from and their knowledge materialized as high-quality training data.
Product Lead at John Snow Labs
Dia Trambitas is a computer scientist with a rich background in Natural Language Processing.
She has a Ph.D. in Semantic Web from the University of Grenoble, France, where she worked on ways of describing spatial and temporal data using OWL ontologies and reasoning based on semantic annotations. She then changed her interest to text processing and data extraction from unstructured documents, a subject she has been working on for the last 10 years. She has a rich experience working with different annotation tools and leading document classification and NER projects in verticals such as Finance, Investment, Banking, and Healthcare.