BlaBla: Linguistic Feature Extraction for Clinical Analysis in Multiple Languages

We introduce BlaBla, an open-source Python library for extracting linguistic\nfeatures with proven clinical relevance to neurological and psychiatric\ndiseases across many languages. BlaBla is a unifying framework for accelerating\nand simplifying clinical linguistic research. The library is built on\nstate-of-the-art NLP frameworks and supports multithreaded/GPU-enabled feature\nextraction via both native Python calls and a command line interface. We\ndescribe BlaBla's architecture and clinical validation of its features across\n12 diseases. We further demonstrate the application of BlaBla to a task\nvisualizing and classifying language disorders in three languages on real\nclinical data from the AphasiaBank dataset. We make the codebase freely\navailable to researchers with the hope of providing a consistent,\nwell-validated foundation for the next generation of clinical linguistic\nresearch.\n