Open Thesis Topics

Students who are eager to develop their skills in a research-oriented thesis in our group should mail us their interests at webis@listserv.uni-weimar.de. Suitable topics are, for example:

  • Adversarial Learning of Writing Style Representations
  • Authorship Identification with Phonological Features
  • Axiomatic Argumentative Web Scale Document Re-ranking
  • Clickbait Spoiling
  • Crowdsourcing the Translation of a Book
  • Dealing with False Memories in Web Search
  • Detecting Bias in Media
  • Detecting Text Reuse from Books
  • Developing a Collaborative Writing Tool for Wikipedia
  • Detecting Bias Amplification in Search Engines
  • Exploiting Argumentation Knowledge Graphs for Argument Generation
  • Exploratory Analysis of Wikipedia Text Reuse
  • Facet Completion based on Term Embeddings
  • Harvesting the Web for Building Evidence-based Knowledge Graphs
  • Neural Netspeak – Exploring the Performance of Transformer Models as Idiomatic Writing Assistants
  • Paraphrasing Operations for Heuristic Author Obfuscation
  • Paraphrasing Texts for Conversational News
  • Re-Ranking for Total Recall in Systematic Reviews
  • Semantic Search Engines for the Analysis of Debates and Discourses
  • Semi-Automatically Supporting Crowdsourcing Approval Processes
  • Simulating Search Behavior
  • Text Mining Methods for Intelligent Writing Assistance
  • The Said and the Unsaid: Analyzing Metaphors using Word Embeddings

Ongoing Theses

  • Nico Reichenbach. Argumentative Image Search (supervised by Johannes Kiesel, Martin Potthast, and Benno Stein)
  • Till Werner. Argument Quality Assessment in Natural Language using Machine Learning (supervised by Henning Wachsmuth)
  • Philipp Rothe. Comparing Keyqueries for different Retrieval Models (supervised by Matthias Hagen)
  • Shaour Haider. Few Shot Learning for Text Classification (supervised by Tim Gollub and Magdalena Wolska)
  • Counterargument Generation via Premise Rebuttal (supervised by Milad Alshomary)
  • Lukas Trautner. Graph-Based Synthesis of Counterfactuals (supervised by Khalid Al-Khatib and Benno Stein)
  • Alexander Rensch. Expertise Filtering for Social Media Timelines (supervised by Matthias Hagen and Martin Potthast)
  • Lukas Gehrke. Gender Regression and Gender Prediction based on Writing Style (supervised by Matti Wiegmann and Martin Potthast)
  • Nick Düsterhus. Snippet Generation for Argument Search (supervised by Milad Alshomary)
  • Hannes Winkler. Geolocation of Social Media Posts (supervised by Matti Wiegmann, Martin Potthast, Magdalena Wolska, and Benno Stein)
  • Lars Meyer. Large-scale Comparison and Analysis of Approaches and Algorithms for Web Page Segmentation (supervised by Johannes Kiesel and Martin Potthast)
  • Fan Fan. Mining High-ethos Evidence from Wikipedia (supervised by Khalid Al-Khatib and Yamen Ajjour)
  • Jan Philipp Bittner. Near-Duplicate-Detection of Webpages (supervised by Maik Fröbe and Matthias Hagen)
  • Salomo Pflugradt. Reproducing Text Alignment Algorithms from PAN (supervised by Shahbaz Syed)
  • Nina Schwanke. Retrieving Police Press Releases for News Verification (supervised by Matthias Hagen and Martin Potthast)
  • Valentin Dittmar. Towards Answering Comparative Web Questions (supervised by Alexander Bondarenko and Matthias Hagen)
  • Unsupervised Metaphor Categorization (supervised by Henning Wachsmuth)
  • Erika Garces. Visualizing Wikipedia Text Reuse. (supervised by Michael Völske, and Patrick Riehmann from the Virtual Reality group)

Contact and Communication

  • Discord: ask staff for access
  • Google Calendar
  • Mailing list staff: webis@listserv.uni-weimar.de
  • Mailing list students: webisstud@listserv.uni-weimar.de
  • Skype: webis
  • Twitter: @webis_de
  • Whereby: webis room

Resources, HowTo Pages, and Notes Files

  • Facilities page: lists hardware, services, thesis templates, and relevant howto pages of the Webis group
  • GitHub: for public websites and published work
  • GitLab: for student repositories and work in progress
  • NFS: for large data (do not use Dropbox)
  • VPN: access the network of the Webis group from public Internet

Meeting Rules

  • Please take notes.
  • Also students should prepare an agenda (not only the PhD).
  • Typical meeting duration: 30 minutes with student assistents, 60 minutes for projects and PhD meetings.
  • Don’t stray off-topic. Respect your students' and PhDs' time respectively.
  • Don’t meet if there is nothing to discuss.