DWS Area: Natural Language Processing, Research

Paper accepted at ICLR 2020: You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings

The paper „You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings“ by Daniel Ruffinelli, Samuel Broscheit and Rainer Gemulla has been accepted at the 2020 International Conference of Learning Representations (ICLR). Abstract: Knowledge graph embedding (KGE) models learn ...

LibKGE knowledge graph embedding library released

LibKGE is a PyTorch-based library for efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). It is highly configurable, easy to use, and extensible.

First PhD Student Poster Session of DWS Colloquium FSS2020

The first DWS PhD Student Poster Session of the FSS2019 DWS Colloquium took place today.

Juniorprofessor on Process Analytics starting in April

We are very happy to announce that Dr. Han van der Aa will be assigned as Juniorprofessor at the School of Business Informatics and Mathematics in April. Dr. van der Aa reseach focus is data-driven process analytics and he will join the DWS group as 8th professor. Welcome!

44.2 billion quads Microdata, Embedded JSON-LD, RDFa, and Microformat data originating from 11.9 million websites published

The DWS group is happy to announce the new release of the WebDataCommons Microdata, JSON-LD, RDFa and Microformat data corpus. The data has been extracted from the November 2019 version of the Common Crawl covering 2.4 billion HTML pages which originate from 32 million websites (pay-level domains).

Christian Bizer gives keynote at JIST 2019

Professor Bizer was invited to give the keynote speech at the 9th Joint International Semantic Technology Conference (JIST2019) in Hangzhou, China.

Christian Bizer wins SWSA Ten-Year Award

We are happy to announce that Professor Christian Bizer has received the SWSA Ten-Year Award at the 18th International Semantic Web Conference (ISWC2019) in Aukland, New Zealand.

WDC Product Data Corpus and Gold Standard for Large-Scale Product Matching Version 2.0 released

We are happy to announce the release of Version 2.0 of the Web Data Commons Product Data Corpus and Gold Standard for Large-Scale Product Matching. The product data corpus consits of 26 million product offers (16 million English language offers) originating from 79 thousand different e-shops. The ...

PhD Student Poster Session

The first DWS PhD Student Poster Session took place this Tuesday. At the poster session, half of the PhD students of the DWS group presented the current status of their research and got feedback and inspiration for next steps from the DWS professors and the other PhD students. The poster session was ...

Open Post-Doc position on political text understanding

We are looking to hire a full-time post-doc (E13 100%) at the Data and Web Science group of the University of Mannheim to work on natural language understanding of political texts - see [1] for an overview of the research area. The successful candidate will contribute to projects B6 and C4 of the ...