Zero-Shot Learning (ZSL) is a new paradigm that has gained massive popularity recently due to its potential of reducing data annotations and high generalisability. In the pursuit of bringing product-ready latest ML research to our community, we have implemented ZSL for two major tasks in Spark NLP for Healthcare: Named Entity Recognition (NER) and Relation Extraction (RE).
In this session, we will explore ZSL models available as part of Spark NLP for healthcare library, how to use them using automatic prompt generation using Q&A models, and finally, how they perform on real data and help reduce data annotation requirements.
Hasham Ul Haq is a Data Scientist at John Snow Labs, and an AI scholar and researcher at PI School of AI. During his carrier, he has worked on numerous projects across various sectors, including healthcare. At John Snow Labs, his primary focus is to build scalable and pragmatic systems for NLP, that are both, production-ready, and give SOTA performance. In particular, he has been working on Span detection, Natural Language Inference, disambiguation, Named Entity Recognition, and a lot more! Hasham also has an active research profile with publications in NeurIPS, AAAI, and multiple scholarship grants and affiliations.
Prior to John Snow Labs, he was leading search engine and knowledge base development at one of Europe’s largest telecom providers. He has also been mentoring startups in computer vision by providing trainings and designing ML architectures.