Web-based Systems Group @ University of Mannheim

MatchGPT

This repository contains code and extensive prompt examples to reproduce and extend the experiments in our papers "Using ChatGPT for Entity Matching" and "Entity Matching using Large Language Models".

contrastive-product-matching

This repository contains the code to reproduce the experiments of the poster "Supervised Contrastive Learning for Product Matching"

productbert-intermediate

This repository contains code and data download scripts for the paper "Intermediate Training of BERT for Product Matching" by Ralph Peeters, Christian Bizer and Goran Glavaš.

ExtractGPT

Attribute Value Extraction using Large Language Models

productCategorization

This repository contains code and data download instructions for the workshop paper "Improving Hierarchical Product Classification using Domain-specific Language Modelling" by Alexander Brinkmann and Christian Bizer.

wdc-lspc-v2

This repository contains code and data download scripts for the paper "Using schema.org annotations for training and maintaining product matchers" by Ralph Peeters, Anna Primpeli, Benedikt Wichtlhuber and Christian Bizer.

jointbert

This repository contains the code and data download links to reproduce the experiments of the PVLDB paper "Dual-Objective Fine-Tuning of BERT for Entity Matching" by Ralph Peeters and Christian Bizer.

wdcproducts

This repository contains the code and data download links to reproduce building the WDC Products Benchmark.

TabAnnGPT

This repository contains the code for the experiments run in the papers "Column Type Annotation using ChatGPT" and "Column Property Annotation using Large Language Models".

SC-Block

SC-Block is a supervised contrastive blocking method which combines supervised contrastive learning for positioning records in an embedding space and nearest neighbour search for candidate set building.

WDCFramework

Java Framework which is used by the Web Data Commons project to extract Microdata, Microformats and RDFa data, Web graphs, and HTML tables from the web crawls provided by the Common Crawl Foundation.

winter

WInte.r is a Java framework for end-to-end data integration. The WInte.r framework implements well-known methods for data pre-processing, schema matching, identity resolution, data fusion, and result evaluation.

EntityMatchingTaskProfiler

Code for profiling entity matching tasks using the dimensions described in the following paper: Primpeli, Anna, and Christian Bizer. "Profiling entity matching benchmark tasks." Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2020.

UnsupervisedBootAL

Unsupervised Bootstrapping of Active Learning for Entity Resolution

wdc-pave

Web Data Commons - Using LLMs for Product Attribute Value Extraction and Normalization

ALMSER-GB

This repository contains the code and data for reproducing the results of the paper "Graph-boosted Active Learning for Multi-Source Entity Resolution" presented at ISWC2021.

wdc-sotab

SubsetCreatorJupyterNBs

Jupyter notebooks used to create the schema.org subsets from the MD and JSON-LD corpus for the WDC 2020 structured data extraction.

TailorMatch

This repository contains code and comprehensive examples to replicate and build upon the experiments presented in our paper “Fine-tuning Large Language Models for Entity Matching” The repository provides resources for implementing fine-tuning techniques on large language models specifically for entity matching tasks.

ALMSER-GEN

This repository contains the code and data for reproducing the results of the paper "Active Learning for Multi-Source Entity Matching: How do the Characteristics of the Task Impact Performance?" .

pie_chatgpt

Product Information Extraction using ChatGPT

schemaorg-tables

This repository contains the code and data download links to reproduce the building process of the 2021 Schema.org Table Corpus.

MannheimSearchJoinsEngine

A Search Join is a join operation which extends a user-provided table with additional attributes based on a large corpus of heterogeneous data originating from the Web or corporate intranets.

wdc-page

This repository contains the source files of the Web Data Commons website and is used to maintain the site. The Web Data Commons project extracts structured data from the Common Crawl

DeepAL_for_ER

Code and Data to reproduce the results of the Master Thesis of Stephan Waitz on "Combining Deep Learning and Active Learning for Entity Resolution"

StructuredDataProfiler

Java project for profiling the results of the yearly Web Data Commons extraction of structured data with RDFa, Microdata, Microformat, and Embedded JSON-LD annotations.

wdc-smb

This repository contains the code and data download links to reproduce building the WDC SMB Benchmark.