Usage of fine-tuned BioBERT for identification of chemical entities

Projects that do not fall under current programmes.

BioCreative VII

Current chemical concept recognition tools have demonstrated significantly lower performance for in full-text articles than in abstracts. Improving automated full-text chemical concept recognition can substantially accelerate manual indexing and curation and advance downstream NLP tasks such as relevant article retrieval. Participating in BioCreative Track NLM-Chem we focus identifying chemicals in full-text articles (i.e. named entity recognition and normalization).

Chemical named entity recognition (NER) is a significant pre-processing task in natural language processing. Identification and extraction of chemical entities from biomedical literature and entities linking to the knowledge base are essential steps for the chemical text-mining pipeline. However, the identification of chemical entities in a biomedical text is a challenging task due to the diverse morphology of chemical entities and the different types of chemical nomenclature. In this work, we ...

BC7 NLM-Chem-track data and materials

This folder contains the python code for developing weighted loss trainer (WeLT) with all the expiremnatal work. Here is the link for our public [GitHub repository] (https://github.com/mobashgr/WELT.git).