@phdthesis{Budig2018,
  author    = {Budig, Benedikt},
  title     = {Extracting Spatial Information from Historical Maps: Algorithms and Interaction},
  edition   = {1. Auflage},
  publisher = {W{\"u}rzburg University Press},
  address   = {W{\"u}rzburg},
  isbn      = {978-3-95826-092-4},
  doi       = {10.25972/WUP-978-3-95826-093-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-160955},
  school      = {W{\"u}rzburg University Press},
  pages     = {viii, 160},
  year      = {2018},
  abstract  = {Historical maps are fascinating documents and a valuable source of information for scientists of various disciplines. Many of these maps are available as scanned bitmap images, but in order to make them searchable in useful ways, a structured representation of the contained information is desirable. This book deals with the extraction of spatial information from historical maps. This cannot be expected to be solved fully automatically (since it involves difficult semantics), but is also too tedious to be done manually at scale. The methodology used in this book combines the strengths of both computers and humans: it describes efficient algorithms to largely automate information extraction tasks and pairs these algorithms with smart user interactions to handle what is not understood by the algorithm. The effectiveness of this approach is shown for various kinds of spatial documents from the 16th to the early 20th century.},
  subject      = {Karte},
  language  = {en}
}
@phdthesis{Dietrich2019,
  author    = {Dietrich, Georg},
  title     = {Ad Hoc Information Extraction in a Clinical Data Warehouse with Case Studies for Data Exploration and Consistency Checks},
  doi       = {10.25972/OPUS-18464},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-184642},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2019},
  abstract  = {The importance of Clinical Data Warehouses (CDW) has increased significantly in recent years as they support or enable many applications such as clinical trials, data mining, and decision making. CDWs integrate Electronic Health Records which still contain a large amount of text data, such as discharge letters or reports on diagnostic findings in addition to structured and coded data like ICD-codes of diagnoses. Existing CDWs hardly support features to gain information covered in texts. Information extraction methods offer a solution for this problem but they have a high and long development effort, which can only be carried out by computer scientists. Moreover, such systems only exist for a few medical domains. This paper presents a method empowering clinicians to extract information from texts on their own. Medical concepts can be extracted ad hoc from e.g. discharge letters, thus physicians can work promptly and autonomously. The proposed system achieves these improvements by efficient data storage, preprocessing, and with powerful query features. Negations in texts are recognized and automatically excluded, as well as the context of information is determined and undesired facts are filtered, such as historical events or references to other persons (family history). Context-sensitive queries ensure the semantic integrity of the concepts to be extracted. A new feature not available in other CDWs is to query numerical concepts in texts and even filter them (e.g. BMI > 25). The retrieved values can be extracted and exported for further analysis. This technique is implemented within the efficient architecture of the PaDaWaN CDW and evaluated with comprehensive and complex tests. The results outperform similar approaches reported in the literature. Ad hoc IE determines the results in a few (milli-) seconds and a user friendly GUI enables interactive working, allowing flexible adaptation of the extraction. In addition, the applicability of this system is demonstrated in three real-world applications at the W{\"u}rzburg University Hospital (UKW). Several drug trend studies are replicated: Findings of five studies on high blood pressure, atrial fibrillation and chronic renal failure can be partially or completely confirmed in the UKW. Another case study evaluates the prevalence of heart failure in inpatient hospitals using an algorithm that extracts information with ad hoc IE from discharge letters and echocardiogram report (e.g. LVEF < 45 ) and other sources of the hospital information system. This study reveals that the use of ICD codes leads to a significant underestimation (31\%) of the true prevalence of heart failure. The third case study evaluates the consistency of diagnoses by comparing structured ICD-10-coded diagnoses with the diagnoses described in the diagnostic section of the discharge letter. These diagnoses are extracted from texts with ad hoc IE, using synonyms generated with a novel method. The developed approach can extract diagnoses from the discharge letter with a high accuracy and furthermore it can prove the degree of consistency between the coded and reported diagnoses.},
  subject      = {Information Extraction},
  language  = {en}
}
@phdthesis{Kluegl2015,
  author    = {Kl{\"u}gl, Peter},
  title     = {Context-specific Consistencies in Information Extraction: Rule-based and Probabilistic Approaches},
  publisher = {W{\"u}rzburg University Press},
  address   = {W{\"u}rzburg},
  isbn      = {978-3-95826-018-4 (print)},
  doi       = {10.25972/WUP-978-3-95826-019-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-108352},
  school      = {W{\"u}rzburg University Press},
  year      = {2015},
  abstract  = {Large amounts of communication, documentation as well as knowledge and information are stored in textual documents. Most often, these texts like webpages, books, tweets or reports are only available in an unstructured representation since they are created and interpreted by humans. In order to take advantage of this huge amount of concealed information and to include it in analytic processes, it needs to be transformed into a structured representation. Information extraction considers exactly this task. It tries to identify well-defined entities and relations in unstructured data and especially in textual documents. Interesting entities are often consistently structured within a certain context, especially in semi-structured texts. However, their actual composition varies and is possibly inconsistent among different contexts. Information extraction models stay behind their potential and return inferior results if they do not consider these consistencies during processing. This work presents a selection of practical and novel approaches for exploiting these context-specific consistencies in information extraction tasks. The approaches direct their attention not only to one technique, but are based on handcrafted rules as well as probabilistic models. A new rule-based system called UIMA Ruta has been developed in order to provide optimal conditions for rule engineers. This system consists of a compact rule language with a high expressiveness and strong development support. Both elements facilitate rapid development of information extraction applications and improve the general engineering experience, which reduces the necessary efforts and costs when specifying rules. The advantages and applicability of UIMA Ruta for exploiting context-specific consistencies are illustrated in three case studies. They utilize different engineering approaches for including the consistencies in the information extraction task. Either the recall is increased by finding additional entities with similar composition, or the precision is improved by filtering inconsistent entities. Furthermore, another case study highlights how transformation-based approaches are able to correct preliminary entities using the knowledge about the occurring consistencies. The approaches of this work based on machine learning rely on Conditional Random Fields, popular probabilistic graphical models for sequence labeling. They take advantage of a consistency model, which is automatically induced during processing the document. The approach based on stacked graphical models utilizes the learnt descriptions as feature functions that have a static meaning for the model, but change their actual function for each document. The other two models extend the graph structure with additional factors dependent on the learnt model of consistency. They include feature functions for consistent and inconsistent entities as well as for additional positions that fulfill the consistencies. The presented approaches are evaluated in three real-world domains: segmentation of scientific references, template extraction in curricula vitae, and identification and categorization of sections in clinical discharge letters. They are able to achieve remarkable results and provide an error reduction of up to 30\% compared to usually applied techniques.},
  subject      = {Information Extraction},
  language  = {en}
}