Scientific Software

DKPro is a collection of open-licensed software projects for natural language processing, which has been initiated by the Ubiquitous Knowledge Processing (UKP) Lab. I am coordinating the following projects:

	DKPro Statistics A collection of open-licensed statistical tools written in Java. Homepage | Publication
	Java Wiktionary Library (JWKTL) Efficient programmatic access to the online dictionary Wiktionary. Homepage | Publication
	Java OmegaWiki Library (JOWKL) Efficient programmatic access to the online dictionary OmegaWiki. Homepage | Publication
	Java OpenThesaurus Library (JOTL) Efficient programmatic access to OpenThesaurus. Homepage

Scientific Data

Highlights:

UBY A large-scale, standardized, and integrated lexical resource. Homepage | Publication

Further data projects:

• Hierarchical Summarization
  Corpus, crowdsourcing and annotation guidelines for hierarchical summarization.
  
  GitHub | Publication
• Live Blog Corpus for Summarization
  Approach to generate a live blog summarization corpus covering data from The Guardian and BBC.
  
  GitHub | Publication
• DBS – A summarization corpus of coherent extracts
  The DBS corpus contains 93 multi-document summaries for 293 German documents about 30 education-related topics.
  
  GitHub | Publication

Experimental Software

• Data-efficient Neural Text Compression
  In this project, we develop a general framework for Interactive Text Compression. We propose an interactive text compression model using active learning learning methods for data-efficient learning.
  
  GitHub | Publication
• Diagnostic Reasoning
  Challenges in the Automatic Analysis of Students' Diagnostic Reasoning
  
  GitHub | Publication
• Sherlock
  Interactive Summarization of Large Text Collections
  
  GitHub | Publication
• APRIL
  Active Preference Reinforcement Learning, for extractive multi-document summarisation
  
  GitHub | Publication
• Document-level Stance Detection
  A Retrospective Analysis of the Fake News Challenge Stance Detection Task
  
  GitHub | Publication
• Concept-Map-Based Multi-Document Summarization
  Structured summarization method based on concept co-reference resolution and global importance optimization.
  
  GitHub | Publication
• Interactive Multi-Document Summarization
  A general framework for interactive multi-document summarization.
  
  GitHub | Publication
• Detection of Cross-lingual Marketing Blunders
  Method, software, and data for getting started with a new NLP task: detecting marketing blunders.
  
  GitHub | Publication
• MDSWriter
  A software for manually creating multi-document summarization corpora and a platform for developing complex annotation tasks spanning multiple steps.
  
  GitHub | Publication
• InViEdit
  A web-based writing environment for evaluating intelligent writing assistance methods.
  
  GitHub | Publication