This repository contains a collection of my open-source work written at work that I'm proud of.

My other publications can be found on ORCID.

Open-Source Code

PLIX

PLIX is a highly modular pipeline for information extraction with SOTA results on the ArtTabGen benchmarking data set.

Source: Zenodo

ArtTabGen Code

Code to generate artificial tables, based on real-world tables containing technical data. The user can specify the technical terms to use for the generation via the input.

Source: Zenodo

A-Match

NFDI4Ing seed fund project lead by me. A-Match is a UI to allow semantic matching of parameters between two APIs.

Source: Zenodo

OntoHuman

OntoHuman is a human-in-the-loop-based suite of tools for ontology enrichment and information extraction. It contains a preliminary version of PLIX.

Source: Zenodo

Open-Source Data Sets

ArtTabGen Data Sets

These data sets can be used to benchmark information extraction systems on artificial tables containing technical data.

Source: Zenodo