DFKI-NLP

All

72 repositories

dfki-nlp.github.io
Public
https://dfki-nlp.github.io
SCSS
•
MIT License
•0•2•0•0•Updated Dec 5, 2024Dec 5, 2024
perseus-textgen
Public
A repository for scripts to run awesomely large language models with text generation inference APIs and (chat) UIs
Shell
•
MIT License
•0•0•3•0•Updated Nov 14, 2024Nov 14, 2024
tohyve-services
Public
Python
•1•1•4•0•Updated Oct 22, 2024Oct 22, 2024
MultiTACRED
Public
[ACL23] This repository contains the code for our paper "MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset"
multilingual nlp machine-learning information-extraction transformer relation-classification
Python
•
MIT License
•0•8•0•0•Updated Oct 16, 2024Oct 16, 2024
pegasus-bridle
Public
Ease your training experience on the DFKI GPU cluster 🦄
Shell
•
Apache License 2.0
•0•5•1•1•Updated Oct 14, 2024Oct 14, 2024
CoXQL
Public
Code for the paper accepted at EMNLP 2024 Findings: "CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems" (Wang et al., 2024)
parsing datasets interpretability conversational-qa
Python
•0•2•0•0•Updated Sep 21, 2024Sep 21, 2024
faq-rewrites-llms
Public
This repository contains the dataset of FAQ texts rewritten using large language models described in our INLG 2024 paper "Enhancing Editorial Tasks: A Case Study on Rewriting Customer Help Page Contents Using Large Language Models".
Creative Commons Attribution Share Alike 4.0 International
•0•0•0•0•Updated Sep 18, 2024Sep 18, 2024
celebrity-corpus
Public
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.
nlp natural-language-processing corpus information-extraction english dataset named-entity-recognition corpus-data ner relation-extraction
Creative Commons Attribution 4.0 International
•1•0•0•0•Updated Sep 17, 2024Sep 17, 2024
CockrACE-corpus
Public
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).
nlp natural-language-processing corpus information-extraction english dataset named-entity-recognition corpus-data ner relation-extraction
XML
•
Creative Commons Attribution 4.0 International
•0•1•0•0•Updated Sep 17, 2024Sep 17, 2024
subjective_text_complexity_corpus
Public
A corpus consisting of German sentences, annotated with subjective complexity ratings by two target groups
Creative Commons Attribution 4.0 International
•0•0•0•0•Updated Sep 17, 2024Sep 17, 2024
sim3s-corpus
Public
Corpus MobASA: a German-language corpus of tweets annotated with their relevance for public transportation, and with sentiment towards aspects related to barrier-free travel.
Python
•
Creative Commons Attribution 4.0 International
•0•2•0•0•Updated Sep 17, 2024Sep 17, 2024
product-corpus
Public
This repository contains the DFKI Product Corpus, a dataset of 174 documents annotated for product and company named entities, and the relation CompanyProvidesProduct.
nlp natural-language-processing corpus information-extraction english dataset named-entity-recognition corpus-data ner relation-extraction
Creative Commons Attribution 4.0 International
•1•12•0•0•Updated Sep 17, 2024Sep 17, 2024
smartdata-corpus
Public
A dataset of almost 2600 German-language documents which has been annotated with fine-grained geo-entities, standard named entity types, and a set of 15 traffic- and industry-related relations.
Creative Commons Attribution 4.0 International
•0•9•0•1•Updated Sep 17, 2024Sep 17, 2024
MobIE
Public
[Konvens21] This repository contains the DFKI MobIE Corpus, a dataset of 3,232 German-language documents that have been annotated with fine-grained geo-entities, such as streets, stops and routes, as well as standard named entity types (organization, date, number, etc).
entity-linking relation-extraction german-language information-extraction dataset named-entity-recognition
Python
•
Creative Commons Attribution 4.0 International
•0•11•0•0•Updated Sep 17, 2024Sep 17, 2024
ADE_templates
Public
This project contains templates and evaluation of models with these templates for the task of Adverse Drug Effect (ADE) detection.
Jupyter Notebook
•
MIT License
•0•1•0•0•Updated Aug 21, 2024Aug 21, 2024
diamat
Public
Machine Translation Diagnostics Tool
nlp machine-learning deep-learning tool machine-translation
Python
•
BSD 3-Clause "New" or "Revised" License
•4•7•1•1•Updated Aug 2, 2024Aug 2, 2024
defx
Public
[SemEval 2020] Defx at SemEval-2020 Task 6: Joint Extraction of Concepts and Relations for Definition Extraction
Jupyter Notebook
•
MIT License
•1•7•0•1•Updated Jul 25, 2024Jul 25, 2024
bias-memit
Public
Mass-Editing Stereotypical Associations to Mitigate Bias in Language Models
Jupyter Notebook
•
MIT License
•0•0•0•0•Updated Jul 18, 2024Jul 18, 2024
DISTRE
Public
[ACL 19] Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction
nlp machine-learning information-extraction transformer relation-extraction distant-supervision multi-task-learning
Python
•
Apache License 2.0
•13•85•4•0•Updated Jun 18, 2024Jun 18, 2024
ACL2024-SymmetricAttentionBert
Public
Jupyter Notebook
•
MIT License
•1•0•0•0•Updated May 27, 2024May 27, 2024
Taxonomy4CL
Public
Taxonomy for Computational Linguistics topics
nlp taxonomy classification computational-linguistics
Python
•
MIT License
•1•1•0•0•Updated May 21, 2024May 21, 2024
weak-supervision-rlhf
Public
Bachelor Thesis: Language Modeling with Reinforcement Learning from Human Feedback with Weak Supervision
Jupyter Notebook
•
Apache License 2.0
•0•2•0•0•Updated May 8, 2024May 8, 2024
nfdi4ds-forc
Public
Repository for constructing a dataset for the Field of Research Classification task.
Jupyter Notebook
•2•1•0•0•Updated Apr 9, 2024Apr 9, 2024
for-classifier
Public
📚 Code for my master's thesis "Investigating Knowledge Injection Approaches for Research Field Classification of Scholarly Articles".
natural-language-processing master-thesis dbpedia classification knowledge-graphs knowledge-injection fields-of-research
Python
•0•1•0•0•Updated Apr 3, 2024Apr 3, 2024
LLMCheckup
Public
Code for the NAACL 2024 HCI+NLP Workshop paper "LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-explanation" (Wang et al. 2024)
nlp interface chatbot dialogue language-models interpretability conversational-ai explainable-ai xai explainability
Python
•1•12•0•0•Updated Mar 24, 2024Mar 24, 2024
keepha_annotation_guidelines
Public
TeX
•0•1•0•0•Updated Mar 22, 2024Mar 22, 2024
radiant
Public
Web RAdio and auDIo processing system for Acessibility aNd Traceability
MIT License
•0•0•0•0•Updated Feb 22, 2024Feb 22, 2024
InterroLang
Public
InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations [EMNLP 2023 Findings]
dialogue transformers data-analysis interpretability xai llms
Python
•1•6•15•4•Updated Oct 23, 2023Oct 23, 2023
semisupervised-mt-qe
Public
Scripts and data to reproduce the experiments of the paper Bhatia et. al 2023, " Semi-supervised learning for Quality Estimation of Machine Translation" - MT Summit 2023
Jupyter Notebook
•
MIT License
•0•1•0•1•Updated Sep 19, 2023Sep 19, 2023
SMV
Public
Code and data for the ACL 2023 NLReasoning Workshop paper "Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods" (Feldhus et al., 2023)
text-classification transformers interpretability explainability integrated-gradients saliency-maps feature-attribution saliency-methods explainable-nlp chatgpt
Python
•1•8•2•0•Updated Jul 27, 2023Jul 27, 2023