Code accompanying the submission "Structural Text Segmentation of Legal Documents" by Aumiller et al.

Package to calculate the similarity score between two sentences

COVID-19 Open Research Dataset Challenge (CORD-19)

Extract ESCO skills and ISCO occupations from texts such as job descriptions or CVs

A python Sentence-Clustering library based on S-Bert and a diverse number of clustering methods. Establishes best number of clusters for each algorithm and the most optimal algorithm by internal and external validation respectively.

Simple Query Based Document Summarization

A Python pipeline to generate responses using GPT3, map them to a vector space using the T5 XXL sentence transformer, use PCA and UMAP dimensionality-reduction methods, and then provide visualizations using Plotly and sentiment analysis using TextBlob

An off-the-shelf grep-like tool that performs semantic similarity search

Qdrant Vector Database + FastAPI

download any (almost) book you want

A conversational AI chatbot framework built on sentence-transformer model.