Skip to content

Model for arXiv text class

  • Description: This is an AI benchmark to evaluate how accurately token classification/named entity recognition is performed with text data, using the arXiv dataset. Here we use accuracy of classification (ACC) to compare how well each model classifies the text data, comparing to the ground truth classification of the arXiv dataset.


Reference(s): https://doi.org/10.1021/acs.jcim.9b00470, https://github.com/usnistgov/chemnlp

Model benchmarks

Model nameDataset Accuracy Team name Dataset size Date submitted Notes
transformers_xlnetmat_scholar_ner0.7481ChemNLP12326701-14-2023CSV, JSON, run.sh, Info