PaDaS-Lab

ir-rag-sigir24-persona-rag

pypads

Building on the MLFlow toolset this project aims to extend the functionality for MLFlow, increase the automation and therefore reduce the workload for the user. The production of structured results is an additional goal of the extension.

simiir-2

SimIIR 2.0 extends the Python-based SimIIR framework for simulating interactive information retrieval (IIR).

pypadre

In this research project, we aim to create an environment to gather structured data about machine learning experiments in order to analyze data and algorithmich dependencies.

pypads-onto

Extension for ontology integrations

pypads-padre

An extension of pypads tracking machine learning workflows (steps and concepts). Most of the concepts are derived from PaDRe.

tempweb24-content-control-study

Code for the paper 'A Longitudinal Study of Content Control Mechanisms' presented at the TempWeb workshop (WWW'24)

antithesis_detection

Official implementation of "Using Pre-Trained Language Models in an End-to-End Pipeline for Antithesis Detection" accepted in LREC-2024

instruct-to-sparql

Instruct-to-SPARQL is a dataset that consists of pairs of Natural language instructions and SPARQL queries. The dataset is created by crawling Wikipedia pages and tutorials for real examples of WikiData SPARQL queries.

intra-class-similarity-guided-distillation

Official implementation of "Intra-Class Similarity-Guided Feature Distillation" accepted in NeurIPS-ENLSP 2023

krony-PT

Compressing GPT2 using Kronecker products.

learn-from-one-specialized-sub-teacher

Official implementation of "Learn From One Specialized Sub-Teacher: One-to-One Mapping for Feature-Based Knowledge Distillation" accepted in EMNLP-Findings 2023

memBERT

Source code for the MemBERT paper

multi-language-dataset-creator

robotstxt-study

A Longitudinal study of robots.txt files extracted from the Common Crawl web archive

url-classification

Classify webpages using their URLs

url-dataset-crawling

Code to crawl content of a dataset of URLs

brwsr

Lightweight Linked Data Browser

Can-GPT-4-Replace-Human-Examiners-A-Competition-on-Checking-Open-Text-Answers

Accompanying code for the paper "Can GPT-4 Replace Human Examiners? A Competition on Checking Open-Text Answers"

mlflow-docker

Production ready docker-compose configuration for ML Flow with Mysql and Minio S3

padre-lab-eu.github.io

Web Page for the PAssau Data science REsearch Lab

Performance-analysis-of-large-language-models-in-the-domain-of-legal-argument-mining

Accompanying code for the paper "Performance analysis of large language models in the domain of legal argument mining"

pypads-examples

Python file examples for PyPads

pypads-notebooks

pypads_examples

This repository includes a set of examples how to use pypads

pypads_jupyter_examples

This repository shows examples how PyPads can be used with a jupyter notebook.

suss-llm

tpdl24-comparative-analysis-user-interactions-in-digital-libraries

This study compares EconBiz (private) and SUSS (public) datasets, revealing EconBiz's more detailed user interactions. It highlights the scarcity of public datasets with rich user data in digital libraries and explores using LLMs to simulate detailed interactions while preserving anonymity, aiming to enhance public datasets for improved research.

wikibase-docker

🐳 Docker images and example compose file for Wikibase and surrounding services

zero-to-jupyterhub-k8s

Helm Chart & Documentation for deploying JupyterHub on Kubernetes