Laura Dietz
Associate Professor
Email: Laura.Dietz@unh.edu
Phone: (603) 862-5429
Office: Kingsbury Hall, Durham, NH 03824
Pronouns: She/Her/Hers
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.
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.
Courses Taught
- CS 696: Independent Study
- CS 752: Foundations of Neural Networks
- CS 752/852: Foundations of Neural Networks
- CS 753/853: Information Retrieval
- CS 758: Algorithms
- CS 758/858: Algorithms
- CS 781/881: DS - Knowledge Graphs and Text
- CS 852: Foundations of Neural Networks
- CS 858: Algorithms
- CS 881: DS - Knowledge Graphs and Text
- CS 953: DS - Knowledge Graphs and Text
- CS 999: Doctoral Research
- DATA 690: Internship Experience
Education
- Ph.D., Computer Science, Max Planck Institute
- M.S., Goethe University, Germany
- B.S., Goethe University, Germany
Research Interests
- Computer Science
- SCIENCE & TECHNOLOGY/MATHEMATICS/COMPUTER SCIENCE
Selected Publications
Dietz, L., Xiong, C., Dalton, J., & Meij, E. (Eds.) (2019). Special issue on knowledge graphs and semantics in text analysis and retrieval \textbf[Special Issue]. In . Springer Netherlands.
Nanni, F., Ponzetto, S. P., Dietz, L., & Machinery, A. C. (2018). Entity-Aspect Linking: Providing Fine-Grained Semantics of Entities in Context. In JCDL'18: PROCEEDINGS OF THE 18TH ACM/IEEE JOINT CONFERENCE ON DIGITAL LIBRARIES (pp. 49-58). doi:10.1145/3197026.3197047
Dalton, J., Dietz, L., & Allan, J. (2014). Entity query feature expansion using knowledge base links. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval (pp. 365-374). ACM.
