dfki-nlp's Projects
📝 Easily create a beautiful website using Academic, Hugo, and Netlify
Mass-Editing Stereotypical Associations to Mitigate Bias in Language Models
The “Celebrity” corpus consists of 150 news articles annotated with three semantic relations of the biographic domain. The corpus is provided in two formats, a CoNLL-like format (plain-text files with tabular-separated values) and an XML-based format. Files in the XML-based format can be loaded with https://github.com/DFKI-NLP/recon.
The “CockrACE” corpus consists of 140 news articles annotated with mentions of entities and their coreference links, as well as relation mentions for the evaluation of relation extraction (RE) experiments. Three semantic relations have been annotated, each of them dealing with people's family relationships (marriages, brother/sister, parent/child).
Claim retrieval and matching with laws for COVID-19 related legislation (LREC 2022).
[LREC 2022] Cross-lingual Approaches for the Detection of Adverse Drug Reactions
Crosslingual Neural Vector Conceptualization
[SemEval 2020] Defx at SemEval-2020 Task 6: Joint Extraction of Concepts and Relations for Definition Extraction
https://dfki-nlp.github.io
Machine Translation Diagnostics Tool
ICU predictions on MIMIC-III with discrete and distributed event representations.
[ACL 19] Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction
An Interactive Tool for Scalable and Reproducible Error Analysis.
Event extraction implementation - Joint classification of events and arguments
The repository for our annotated corpus of textual explanations for clinical decision support.
Few-shot named entity recognition
A very simple framework for state-of-the-art NLP
📚 Code for my master's thesis "Investigating Knowledge Injection Approaches for Research Field Classification of Scholarly Articles".
Code and data for the paper "Evaluating German Transformer Language Models with Syntactic Agreement Tests" (Zaczynska et al., 2020)
InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations [EMNLP 2023 Findings]
Minimalist NMT for educational purposes
Learning Explanations from Language Data
LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools
[ACL-ECNLP 2020] Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers
Dockerfiles for providing a compiled version of the Marian neural machine translation toolkit