Resources

The following list gives a short description of the available resources:

Datasets

• EUR-Lex text collection

  The EUR-Lex text collection provides a large multlabel classification benchmark with up to 4000 different classes.
  

• Datasets for Graded Multilabel Classification
  

  The known BeLaE Dataset and two new datasets from medical text classification and movie ratings.
  

• Incident-Related Twitter Datasets

  These datasets comprise labeled tweets from 10 major cities in the English-speaking world. The tweets were selected and labeled for the domain of incident detection.

• Medical Concept Embeddings
  

  Concept vector representations learned from a large labeled background corpus. These were used for computing the semantic similarity between terms from the medical domain.
  

Ontologies

• UI² Ontology

  The UI² Ontology is a formal ontology for describing user interfaces, their components, and the possible interactions with them.
  

Software

• Computer Poker Bots

  A small repository of Computer Poker Bots.

• Attachment Checker

  A Thunderbird plugin that learns to warn you when you forget to attach a file to your message.

• Classification GUI

  A graphical user interface that allows to intuitively assign concepts from an ontology to a set of documents in order to quickly and easily develop a (multilabel) classification dataset.

• Peewit

  A light-weight meta-framework for machine learning experiments.

• FeGeLOD

  A tool for generating machine-learning features from Linked Open Data.
  

• Explain-a-LOD

  A tool for generating possible explanations for statistics based on Linked Open Data.
  

• SeCo

  A framework for Separate-and-Conquer Rule Learning.
  

• Perceptrovement

  A highly modular framework for the efficient Perceptron algorithm containing a great collection of effective extensions
  

• MoB4LOD

  A framework for creating customized browser applications for Linked Open Data
  

• JFreeWebSearch

  A free (i.e., no registration and API key required) Java library to perform searches on the web
  

• Ontology Matching Tools
  

  The KE group has developed a variety of ontology matching tools.

• Graded Multilabel Classification, Code and Data
  The code and data used for our paper about pairwise graded multilabel classification. In this setting, a label is not only present or absent, but can have several grades, e.g. stars.
• P³oodle
  A browser extension/add-on for personalized privacy-protected web search.
• AiTextML
  Learn continuous vector representations jointly for words, documents, and labels. Use corpora with labelled documents and use also descriptions of labels. This enables also to do zero-shot learning, i.e., to predict labels for which no documents were observed during training.

Computing

• Students Pool

   Students who are active in our group have the possibility to use our infrastructure and our pool with six Linux-based computers in room D205.
  

• Students Computing Infrastructure
  

  Get to know our research computing cluster.