My research combines methods for text retrieval, extraction, machine learning and analytics (TREMA).
Currently, I am working on methods that automatically, and in a query-driven manner, retrieve materials from the Web and compose Wikipedia-like articles. Especially for information needs, where the user has very little prior knowledge about, the web search paradigm of 10 blue hyperlinks is not sufficient. Instead, I envision to provide a synthesis of the Web materials to give a comprehensive overview (TREC CAR).
My goal is to develop algorithm to find what users are looking for based on text content only. In contrast, most Web-search algorithms are based on interaction data such as query-log, click, or session information---information that is not available when searching private document collections. Consequently, we aim to maximize the utility of information retrieval models in combination with methods from natural language processing.
A particular emphasis of my work is to utilize information from structured knowledge bases such as Wikipedia, Freebase, or DBpedia together with text-based reasoning on general document and Web corpora (KG4IR). In my work on "Entity Query Feature Expansion" (SIGIR 2014), I demonstrate that significantly better search results are obtained when using entity linking and knowledge bases in the retrieval algorithm.
