Laura Dietz's research combines methods for text retrieval, extraction, machine learning and analytics (TREMA). Currently, she is working on methods that automatically, and in a query-driven manner, retrieve materials from the web and compose Wikipedia-like articles. Particularly in situations in which the user has very little prior knowledge about a topic, the web search paradigm of 10 blue hyperlinks is not sufficient, she claims. Instead, she is looking at ways to provide a synthesis of web materials to give a comprehensive overview (TREC CAR).

Her goal is to develop algorithms 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, her aim is to maximize the utility of information retrieval models in combination with methods from natural language processing.  One of her particular interests 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 her work on "Entity query feature expansion using knowledge base links" (SIGIR 2014), she demonstrates that significantly better search results are obtained when using entity linking and knowledge bases in the retrieval algorithm.