Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art

Citations Over TimeTop 1% of 2020 papers

Abstract

A large array of pretrained models are available to the biomedical NLP (BioNLP) community. Finding the best model for a particular task can be difficult and time-consuming. For many applications in the biomedical and clinical domains, it is crucial that models can be built quickly and are highly accurate. We present a large-scale study across 18 established biomedical and clinical NLP tasks to determine which of several popular open-source biomedical and clinical NLP models work well in different settings. Furthermore, we apply recent advances in pretraining to train new biomedical language models, and carefully investigate the effect of various design choices on downstream performance. Our best models perform well in all of our benchmarks, and set new State-of-the-Art in 9 tasks. We release these models in the hope that they can help the community to speed up and increase the accuracy of BioNLP and text mining applications.

Related Papers

• → Community challenges in biomedical text mining over 10 years: success, failure and the future(2015)226 cited
• → Biomedical event extraction based on GRU integrating attention mechanism(2018)42 cited
• Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing: Shared Task(2009)
• → Exploring Biomedical Text Processing and Event Extraction(2020)
• → Proceedings of the Workshop on BioNLP Shared Task - BioNLP '09(2009)