Explaining Relation Classification Models with Semantic Extents

2 code implementations • 4 Aug 2023 • Lars Klöser, Andre Büsgen, Philipp Kohl, Bodo Kraft, Albert Zündorf

We introduce semantic extents, a concept to analyze decision patterns for the relation classification task.

Classification Relation +1

ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP

1 code implementation • 1 Aug 2023 • Philipp Kohl, Nils Freyer, Yoka Krämer, Henri Werth, Steffen Wolf, Bodo Kraft, Matthias Meinecke, Albert Zündorf

Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process.

Active Learning

Multi-Attribute Relation Extraction (MARE) -- Simplifying the Application of Relation Extraction

1 code implementation • 17 Nov 2021 • Lars Klöser, Philipp Kohl, Bodo Kraft, Albert Zündorf

Extracting relations with an arbitrary amount of attributes requires complex systems and costly relation-trigger annotations to assist these systems.

Attribute Binary Relation Extraction +3

STAMP 4 NLP -- An Agile Framework for Rapid Quality-Driven NLP Applications Development

no code implementations • 16 Nov 2021 • Philipp Kohl, Oliver Schmidts, Lars Klöser, Henri Werth, Bodo Kraft, Albert Zündorf

The progress in natural language processing (NLP) research over the last years, offers novel business opportunities for companies, as automated user interaction or improved data analysis.