Skip to content
@DFKI-NLP

DFKI-NLP

Speech and Language Technology (SLT) Group of the Berlin lab of the German Research Center for Artificial Intelligence (DFKI)

Popular repositories Loading

  1. thermostat thermostat Public

    Collection of NLP model explanations and accompanying analysis tools

    Jsonnet 143 8

  2. TRE TRE Public

    [AKBC 19] Improving Relation Extraction by Pre-trained Language Representations

    Python 108 12

  3. DISTRE DISTRE Public

    [ACL 19] Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction

    Python 85 13

  4. tacrev tacrev Public

    [ACL 20] TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task

    Jupyter Notebook 69 8

  5. RelEx RelEx Public

    RelEx - A simple framework for Relation Extraction built on AllenNLP

    Jsonnet 16 1

  6. REval REval Public

    [ACL 20] Probing Linguistic Features of Sentence-level Representations in Neural Relation Extraction

    Python 13 4

Repositories

Showing 10 of 71 repositories
  • DFKI-NLP/dfki-nlp.github.io’s past year of commit activity
    TeX 2 MIT 0 0 0 Updated Sep 18, 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".

    DFKI-NLP/faq-rewrites-llms’s past year of commit activity
    0 CC-BY-SA-4.0 0 0 0 Updated Sep 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.

    DFKI-NLP/celebrity-corpus’s past year of commit activity
    0 CC-BY-4.0 1 0 0 Updated Sep 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).

    DFKI-NLP/CockrACE-corpus’s past year of commit activity
    XML 1 CC-BY-4.0 0 0 0 Updated Sep 17, 2024
  • subjective_text_complexity_corpus Public

    A corpus consisting of German sentences, annotated with subjective complexity ratings by two target groups

    DFKI-NLP/subjective_text_complexity_corpus’s past year of commit activity
    0 CC-BY-4.0 0 0 0 Updated Sep 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.

    DFKI-NLP/sim3s-corpus’s past year of commit activity
    Python 2 CC-BY-4.0 0 0 0 Updated Sep 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.

    DFKI-NLP/product-corpus’s past year of commit activity
    12 CC-BY-4.0 2 0 0 Updated Sep 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.

    DFKI-NLP/smartdata-corpus’s past year of commit activity
    8 CC-BY-4.0 0 0 1 Updated Sep 17, 2024
  • perseus-textgen Public

    A repository for scripts to run awesomely large language models with text generation inference APIs and (chat) UIs

    DFKI-NLP/perseus-textgen’s past year of commit activity
    Shell 0 MIT 0 3 0 Updated Sep 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).

    DFKI-NLP/MobIE’s past year of commit activity
    Python 11 CC-BY-4.0 0 0 0 Updated Sep 17, 2024

Top languages

Loading…

Most used topics

Loading…