Benjamin Senst's starred repositories
awesome-document-understanding
A curated list of resources for Document Understanding (DU) topic
Transform-to-Open-Science
Transformation to Open Science
streamlit-keyup
Streamlit text input that returns value on keyup
nervaluate
Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13
alexandria3k
Local relational access to openly-available publication data sets
RAG_on_FHIR
Work on using Retrieval-Augmented Generation (RAG) to combine Fast Healthcare Interoperable Resources (FHIR) with Generative AI.
TextComplexityDE
TextComplexityDE dataset consists of 1000 sentences in the German language with subjective complexity rating, collected from German learners in level B, and 250 sentences with a native speaker's simplification.
lexica-corpus
Files & script for lexica corpus for German text simplification
you-shall-not-pass
Code and Material for talk at PyConDE2024
board_certification
A personalized learning environment build with Streamlit.
Text-De-Identifizierer
Automatic removal of direct personal identifiers
st-milvus-connection
Connect your streamlit app to milvus database. Open-source contribution to the Streamlit community.
AnonCATDemo
The Deidentify app uses MedCAT to automatically redact or replace sensitive information in documents. Customisable rules and batch processing make it easy to handle large datasets.