Name: NLM/NCBI BioNLP Research Group (PI: Zhiyong Lu)
Type: Organization
Bio: These tools are the results of research conducted in the Computational Biology Branch, NLM/NCBI. More information about NLM/NCBI's disclaimer policy is availabl
Blog: https://www.ncbi.nlm.nih.gov/research/bionlp
NLM/NCBI BioNLP Research Group (PI: Zhiyong Lu)'s Projects
Abbreviation definition dection library trained on PubMed abstracts
Evaluation scripts for BioCreative VI Precision Medicine Track
Tool that converts between BioC XML files and BioC JSON files
BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences
BLUE benchmark consists of five different biomedicine text-mining tasks with ten corpora.
BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).
COVID-19-CT-CXR, a public database of COVID-19 CXR and CT images
A convolutional neural network model for relation extraction.
:eyes: DeepSeeNet is a deep learning framework for classifying patient-based age-related macular degeneration severity in retinal color fundus photographs.
Web interface that allows users to perform computer-assisted text annotation
Benchmarking the medical calculation capabilities of large language models.
ML-Net is a novel end-to-end deep learning framework for multi-label classification of biomedical tasks. ML-Net combines the label prediction network with a label count prediction network, which can determine the output labels based on both label confidence scores and document context in an end-to-end manner.
Software library for building a large-scale data infrastructure for text mining
:newspaper: High-performance tool for negation and uncertainty detection in radiology reports
PhenoTagger
Machine-learning based pipeline relying on LambdaMART currently used in PubMed for relevance (Best Match) searches
General-purpose tagger for joint named entity recognition and normalization. Includes models for both diseases and chemicals (drugs) in biomedical publications.
Text annotation tool for team collaboration
Code and data for TrialGPT.