Dataset and code for 'AI-based Knowledge Extraction from the Bioprinting Literature for identifying technology trends'

Zip file containing the dataset and code for the paper 'AI-based Knowledge Extraction from the Bioprinting Literature for identifying technology trends'. The dataset is composed of:

A train_data.csv file, containing all annotated keywords used for classifier training.

A filt_ls.pkl file, containing the sentences used to train the embeddings model.

A train.py file, to train the composite keyword annotation model.

The authors acknowledge the supported by the European Union’s Horizon 2020 research and innovation program under the project GIOTTO: “Giotto: Active ageing and osteoporosis: The next challenge for smart nanobiomaterials and 3D technologies,” grant agreement no. 814410.