Centralized access to the resources of the
CAROLL Research Group
All
Datasets
Language models
Papers
Projects
Presentations
Datasets
Clean OpenLegalData - German
German Legal Reference Annotations
Model Output of GPT-3.5 and GPT-4 for ECHR-AM
Demos
RE with NER
NER Demos (German Legal NER, GDPR Privacy Policy NER)
RE (Relation Extraction) Demo
Language models
German BERT for Legal NER
GDPR Privacy policy NER
HateBERT: Retraining BERT for Abusive Language Detection in English
Papers
2024
The Elephant in the Room: Ten Challenges of Computational Detection of Rhetorical Figures
Using Pre-Trained Language Models in an End-to-End Pipeline for Antithesis Detection
Impact of Position Bias on Language Models in Token Classification
Status Quo der Entwicklungen von Ontologien Rhetorischer Figuren in Englisch, Deutsch und Serbisch
A Framework for Studying Communication Pathways in Machine Learning-Based Agent-to-Agent Communication
2023
German BERT Model for Legal Named Entity Recognition
A Dataset of German Legal Reference Annotations
Hidden in Plain Sight: Can German Wiktionary and Wordnets Facilitate the Detection of Antithesis?
Multilingual Domain Ontologies of Rhetorical Figures and Their Applications
The Multilingual Twitter Discourse on Vaccination in Germany During the Covid-19 Pandemic
Exploring Semantic Similarity Between German Legal Texts and Referred Laws
Learn From One Specialized Sub-Teacher: One-to-One Mapping for Feature-Based Knowledge Distillation
ESTHER: Ontology of Rhetorical Figures in English
Performance analysis of large language models in the domain of legal argument mining
2022
Towards A Unified Multilingual Ontology For Rhetorical Figures
GRhOOT: Ontology of Rhetorical Figures in German
Network Analysis of German COVID-19 Related Discussions on Telegram
Experiments on Properties of Hidden Structures of Sparse Neural Networks
2021
HateBERT: Retraining BERT for Abusive Language Detection in English
Projects
Wiktionary Parser to Extract German Antonyms
ESTHER-Ontology
GRhOOT-Ontology
Pretrained LM Antithesis Detection
Using Pre-Trained Language Models in an End-to-End Pipeline for Antithesis Detection
Learn From One Specialized Sub-Teacher: One-to-One Mapping for Feature Based Knowledge Distillation
Intra-Class Similarity-Guided Feature Distillation
Build Basic Transformer From Scratch
Performance analysis of large language models in the domain of legal argument mining
Presentations
Using Pre-Trained Language Models in an End-to-End Pipeline for Antithesis Detection
GRhOOT: Ontology of Rhetorical Figures in German
EMNLP 2023 - Learn From One Specialized Sub-Teacher: One-to-One Mapping for Feature Based Knowledge Distillation
ICML 2023 - Learn From One Specialized Sub-Teacher: One-to-One Mapping for Feature Based Knowledge Distillation
