DWS Area: Web-based Systems

Ralph Peeters has successfully defended his PhD Thesis

Ralph Peeters has successfully defended his PhD thesis titled “Entity Matching using Deep Neural Networks: From Discriminative Pre-trained Language Models to Generative Large Language Models” today.

WDC JSON-LD/Microdata/RDFa Data Corpus 2024 published

We are happy to announce the 2024 release of the WebDataCommons Microdata, JSON-LD and RDFa Data Corpus.

Best Paper Award at iiWAS 2024

We are pleased to announce that the paper “ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction” by Alexander Brinkmann, Roee Shraga, and Christian Bizer was awarded as best paper at the 26th International Conference on Information Integration and Web ...

Paper accepted at EDBT 2025

We are happy to announce that the paper “Entity Matching using Large Language Models” by Ralph Peeters, Aaron Steiner, and Christian Bizer has been accepted for the 28th International Conference on Extending Database Technology, taking place from March 25th to March 28th, 2025 in Barcelona, Spain.

Paper accepted for ADBIS 2024

We are pleased to announce that the following paper from the DWS group has been accepted for the 28th European Conference on Advances in Databases and Information Systems as a full paper: “Using LLMs for the Extraction and Normalization of Product Attribute Values” by Alexander Brinkmann, Nick ...

Three papers accepted for ESWC 2024

We are happy to announce that three papers from the DWS group have been accepted to the 21st European Semantic Web Conference: 1. “SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines” by Alexander Brinkmann, Roee Shraga and Christian Bizer has been accepted for the ...

WDC JSON-LD/Microdata/RDFa Data Corpus and WDC Schema.org Table Corpus 2023 published

We are happy to announce the 2023 release of the WebDataCommons Microdata, JSON-LD and RDFa Data Corpus as well as the release of the WebDataCommons schema.org Table Corpus.

Prof. Bizer gives keynote at WebIST conference comparing GPT4 and BERT for Web Data Integration

Prof. Christian Bizer has given a keynote talk comparing the utility of GPT4 and BERT for Web Data Integration at the 19th International Conference on Web Information Systems and Technologies (WEBIST) in Rome.

Best Paper Award at VLDB Tabular Data Analysis Workshop

We are happy to announce that the paper “Column Type Annotation using ChatGPT” by Keti Korini and Christian Bizer has won the best paper award of the Tabular Data Analysis (TaDa) workshop at VLDB 2023 in Vancouver, Canada.

Paper accepted at EDBT 2024

The paper “WDC Products: A Multi-Dimensional Entity Matching Benchmark” by Ralph Peeters, Reng Chiz Der and Christian Bizer has been accepted at EDBT2024.