Research
Our research topics are centered around large unstructured datasets, mostly textual data. We are working at the interface of the fields of information retrieval (IR) and natural language processing (NLP). We do research on topics like:
- Supporting humans searching the web (query understanding, comparative questions, user simulation and abstractive snippets)
- Analyzing large web crawls (near-duplicates and ad-hoc search)
- Identifying good arguments (argument mining and argument search)
- Analyzing and supporting human writing processes (authorship and paraphrasing)
- Understanding how we will (soon) communicate with many tools (conversational interfaces)
Ongoing Third-party Projects
- ACQuA: Answering Comparative Questions with Arguments (funded by the DFG)
- SINIR: Simulating INteractive Information Retrieval (funded by the DFG)
Other Projects
- Args.meExternal link: First Web Search Engine for Arguments
- ArguanaExternal link: Argumentation Analysis for the Web
- Conversational SearchExternal link
- Learning to Rank with Implicit User Feedback
- Near-Duplicates in Web Crawls
- Query Understanding with Entity Linking
- Total Recall for Systematic Reviews
- Web Archive AnalyticsExternal link
Completed Third-party Projects
- Conversational News (funded by the Google Digital News Initiative)
Find further research projects on the website of the Webis GroupExternal link.