SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data
This addresses the problem of data scarcity in biomedical NER for researchers and practitioners, offering a faster alternative to manual annotation, though it is incremental as it builds on weak supervision methods.
The paper tackles biomedical named entity recognition without labeled data by using lexicons as weak supervision and a generative model to denoise it, achieving competitive scores with state-of-the-art supervised benchmarks and enabling one expert to match a crowdsourced approach within 5.1% in 24 hours.
We present SwellShark, a framework for building biomedical named entity recognition (NER) systems quickly and without hand-labeled data. Our approach views biomedical resources like lexicons as function primitives for autogenerating weak supervision. We then use a generative model to unify and denoise this supervision and construct large-scale, probabilistically labeled datasets for training high-accuracy NER taggers. In three biomedical NER tasks, SwellShark achieves competitive scores with state-of-the-art supervised benchmarks using no hand-labeled training data. In a drug name extraction task using patient medical records, one domain expert using SwellShark achieved within 5.1% of a crowdsourced annotation approach -- which originally utilized 20 teams over the course of several weeks -- in 24 hours.