Structure Normalization in Chemical Extraction from Patents
SureChem provides a short review of the implementation of ChemAxon’s Structure Checker and Standardizer in their patent chemistry data generation pipeline. SureChem uses a fully automated system to extract chemical structures from patent text and images. Generating reliable data requires a robust structure filtration and normalization process. A brief description of SureChem's 'best practices' ” is provided, along with a critique of the current state of technology.