@phdthesis{Weigend2007,
  author    = {Weigend, Michael},
  title     = {Intuitive Modelle der Informatik},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-940793-08-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-15787},
  school      = {Universit{\"a}t Potsdam},
  pages     = {331},
  year      = {2007},
  abstract  = {Intuitive Modelle der Informatik sind gedankliche Vorstellungen {\"u}ber informatische Konzepte, die mit subjektiver Gewissheit verbunden sind. Menschen verwenden sie, wenn sie die Arbeitsweise von Computerprogrammen nachvollziehen oder anderen erkl{\"a}ren, die logische Korrektheit eines Programms pr{\"u}fen oder in einem kreativen Prozess selbst Programme entwickeln. Intuitive Modelle k{\"o}nnen auf verschiedene Weise repr{\"a}sentiert und kommuniziert werden, etwa verbal-abstrakt, durch ablauf- oder strukturorientierte Abbildungen und Filme oder konkrete Beispiele. Diskutiert werden in dieser Arbeit grundlegende intuitive Modelle f{\"u}r folgende inhaltliche Aspekte einer Programmausf{\"u}hrung: Allokation von Aktivit{\"a}t bei einer Programmausf{\"u}hrung, Benennung von Entit{\"a}ten, Daten, Funktionen, Verarbeitung, Kontrollstrukturen zur Steuerung von Programml{\"a}ufen, Rekursion, Klassen und Objekte. Mit Hilfe eines Systems von Online-Spielen, der Python Visual Sandbox, werden die psychische Realit{\"a}t verschiedener intuitiver Modelle bei Programmieranf{\"a}ngern nachgewiesen und fehlerhafte Anwendungen (Fehlvorstellungen) identifiziert.},
  language  = {de}
}
@misc{Trapp2007,
  type      = {Master Thesis},
  author    = {Trapp, Matthias},
  title     = {Analysis and exploration of virtual 3D city models using 3D information lenses},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-13930},
  school      = {Universit{\"a}t Potsdam},
  year      = {2007},
  abstract  = {This thesis addresses real-time rendering techniques for 3D information lenses based on the focus \& context metaphor. It analyzes, conceives, implements, and reviews its applicability to objects and structures of virtual 3D city models. In contrast to digital terrain models, the application of focus \& context visualization to virtual 3D city models is barely researched. However, the purposeful visualization of contextual data of is extreme importance for the interactive exploration and analysis of this field. Programmable hardware enables the implementation of new lens techniques, that allow the augmentation of the perceptive and cognitive quality of the visualization compared to classical perspective projections. A set of 3D information lenses is integrated into a 3D scene-graph system: • Occlusion lenses modify the appearance of virtual 3D city model objects to resolve their occlusion and consequently facilitate the navigation. • Best-view lenses display city model objects in a priority-based manner and mediate their meta information. Thus, they support exploration and navigation of virtual 3D city models. • Color and deformation lenses modify the appearance and geometry of 3D city models to facilitate their perception. The presented techniques for 3D information lenses and their application to virtual 3D city models clarify their potential for interactive visualization and form a base for further development.},
  language  = {en}
}
@misc{Piesker2007,
  type      = {Master Thesis},
  author    = {Piesker, Bj{\"o}rn},
  title     = {Constraint-basierte Generierung realit{\"a}tsnaher Eisenbahnnetze},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-15325},
  school      = {Universit{\"a}t Potsdam},
  year      = {2007},
  abstract  = {Diese Arbeit befasst sich mit der Entwicklung einer Applikation, welche Infrastrukturdaten {\"u}ber Eisenbahnnetze generiert. Dabei bildet die Erzeugung der topologischen Informationen den Schwerpunkt dieser Arbeit. Der Anwender charakterisiert hierf{\"u}r vorab das gew{\"u}nschte Eisenbahnnetz, wobei die geforderten Eigenschaften die Randbedingungen darstellen, die bei der Synthese zu beachten sind. Zur Einhaltung dieser Bedingungen wird die Constraint-Programmierung eingesetzt, welche durch ihr spezielles Programmierparadigma konsistente L{\"o}sungen effizient erzeugt. Dies wird u.a. durch die Nachnutzung so genannter globaler Constraints erreicht. Aus diesem Grund wird insbesondere auf den Einsatz der Constraint-Programmierung bei der Modellierung und Implementierung der Applikation eingegangen.},
  language  = {de}
}
@misc{Kirchner2007,
  type      = {Master Thesis},
  author    = {Kirchner, Peter},
  title     = {Verteilte Autorisierung innerhalb von Single Sign-On-Umgebungen : Analyse, Architektur und Implementation eines Frameworks f{\"u}r verteilte Autorisierung in einer ADFS-Umgebung},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-22289},
  school      = {Universit{\"a}t Potsdam},
  year      = {2007},
  abstract  = {Aktuelle Softwaresysteme erlauben die verteilte Authentifizierung von Benutzern {\"u}ber Ver-zeichnisdienste, die sowohl im Intranet als auch im Extranet liegen und die {\"u}ber Dom{\"a}nen-grenzen hinweg die Kooperation mit Partnern erm{\"o}glichen. Der n{\"a}chste Schritt ist es nun, die Autorisierung ebenfalls aus der lokalen Anwendung auszulagern und diese extern durchzu-f{\"u}hren - vorzugsweise unter dem Einfluss der Authentifizierungspartner. Basierend auf der Analyse des State-of-the-Art wird in dieser Arbeit ein Framework vorges-tellt, das die verteilte Autorisierung von ADFS (Active Directory Federation Services) authenti-fizierten Benutzern auf Basis ihrer Gruppen oder ihrer pers{\"o}nlichen Identit{\"a}t erm{\"o}glicht. Es wird eine prototypische Implementation mit Diensten entwickelt, die f{\"u}r authentifizierte Be-nutzer Autorisierungsanfragen extern delegieren, sowie ein Dienst, der diese Autorisierungs-anfragen verarbeitet. Zus{\"a}tzlich zeigt die Arbeit eine Integration dieses Autorisierungs-Frameworks in das .NET Framework, um die praxistaugliche Verwendbarkeit in einer aktuel-len Entwicklungsumgebung zu demonstrieren. Abschließend wird ein Ausblick auf weitere Fragestellungen und Folgearbeiten gegeben.},
  language  = {de}
}
@phdthesis{Blum2010,
  author    = {Blum, Niklas},
  title     = {Formalization of a converged internet and telecommunications service environment},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51146},
  school      = {Universit{\"a}t Potsdam},
  year      = {2010},
  abstract  = {The programmable network envisioned in the 1990s within standardization and research for the Intelligent Network is currently coming into reality using IPbased Next Generation Networks (NGN) and applying Service-Oriented Architecture (SOA) principles for service creation, execution, and hosting. SOA is the foundation for both next-generation telecommunications and middleware architectures, which are rapidly converging on top of commodity transport services. Services such as triple/quadruple play, multimedia messaging, and presence are enabled by the emerging service-oriented IPMultimedia Subsystem (IMS), and allow telecommunications service providers to maintain, if not improve, their position in the marketplace. SOA becomes the de facto standard in next-generation middleware systems as the system model of choice to interconnect service consumers and providers within and between enterprises. We leverage previous research activities in overlay networking technologies along with recent advances in network abstraction, service exposure, and service creation to develop a paradigm for a service environment providing converged Internet and Telecommunications services that we call Service Broker. Such a Service Broker provides mechanisms to combine and mediate between different service paradigms from the two domains Internet/WWW and telecommunications. Furthermore, it enables the composition of services across these domains and is capable of defining and applying temporal constraints during creation and execution time. By adding network-awareness into the service fabric, such a Service Broker may also act as a next generation network-to-service element allowing the composition of crossdomain and cross-layer network and service resources. The contribution of this research is threefold: first, we analyze and classify principles and technologies from Information Technologies (IT) and telecommunications to identify and discuss issues allowing cross-domain composition in a converging service layer. Second, we discuss service composition methods allowing the creation of converged services on an abstract level; in particular, we present a formalized method for model-checking of such compositions. Finally, we propose a Service Broker architecture converging Internet and Telecom services. This environment enables cross-domain feature interaction in services through formalized obligation policies acting as constraints during service discovery, creation, and execution time.},
  language  = {en}
}
@phdthesis{Brauer2010,
  author    = {Brauer, Falk},
  title     = {Extraktion und Identifikation von Entit{\"a}ten in Textdaten im Umfeld der Enterprise Search},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-51409},
  school      = {Universit{\"a}t Potsdam},
  year      = {2010},
  abstract  = {Die automatische Informationsextraktion (IE) aus unstrukturierten Texten erm{\"o}glicht v{\"o}llig neue Wege, auf relevante Informationen zuzugreifen und deren Inhalte zu analysieren, die weit {\"u}ber bisherige Verfahren zur Stichwort-basierten Dokumentsuche hinausgehen. Die Entwicklung von Programmen zur Extraktion von maschinenlesbaren Daten aus Texten erfordert jedoch nach wie vor die Entwicklung von dom{\"a}nenspezifischen Extraktionsprogrammen. Insbesondere im Bereich der Enterprise Search (der Informationssuche im Unternehmensumfeld), in dem eine große Menge von heterogenen Dokumenttypen existiert, ist es oft notwendig ad-hoc Programm-module zur Extraktion von gesch{\"a}ftsrelevanten Entit{\"a}ten zu entwickeln, die mit generischen Modulen in monolithischen IE-Systemen kombiniert werden. Dieser Umstand ist insbesondere kritisch, da potentiell f{\"u}r jeden einzelnen Anwendungsfall ein von Grund auf neues IE-System entwickelt werden muss. Die vorliegende Dissertation untersucht die effiziente Entwicklung und Ausf{\"u}hrung von IE-Systemen im Kontext der Enterprise Search und effektive Methoden zur Ausnutzung bekannter strukturierter Daten im Unternehmenskontext f{\"u}r die Extraktion und Identifikation von gesch{\"a}ftsrelevanten Entit{\"a}ten in Doku-menten. Grundlage der Arbeit ist eine neuartige Plattform zur Komposition von IE-Systemen auf Basis der Beschreibung des Datenflusses zwischen generischen und anwendungsspezifischen IE-Modulen. Die Plattform unterst{\"u}tzt insbesondere die Entwicklung und Wiederverwendung von generischen IE-Modulen und zeichnet sich durch eine h{\"o}here Flexibilit{\"a}t und Ausdrucksm{\"a}chtigkeit im Vergleich zu vorherigen Methoden aus. Ein in der Dissertation entwickeltes Verfahren zur Dokumentverarbeitung interpretiert den Daten-austausch zwischen IE-Modulen als Datenstr{\"o}me und erm{\"o}glicht damit eine weitgehende Parallelisierung von einzelnen Modulen. Die autonome Ausf{\"u}hrung der Module f{\"u}hrt zu einer wesentlichen Beschleu-nigung der Verarbeitung von Einzeldokumenten und verbesserten Antwortzeiten, z. B. f{\"u}r Extraktions-dienste. Bisherige Ans{\"a}tze untersuchen lediglich die Steigerung des durchschnittlichen Dokumenten-durchsatzes durch verteilte Ausf{\"u}hrung von Instanzen eines IE-Systems. Die Informationsextraktion im Kontext der Enterprise Search unterscheidet sich z. B. von der Extraktion aus dem World Wide Web dadurch, dass in der Regel strukturierte Referenzdaten z. B. in Form von Unternehmensdatenbanken oder Terminologien zur Verf{\"u}gung stehen, die oft auch die Beziehungen von Entit{\"a}ten beschreiben. Entit{\"a}ten im Unternehmensumfeld haben weiterhin bestimmte Charakteristiken: Eine Klasse von relevanten Entit{\"a}ten folgt bestimmten Bildungsvorschriften, die nicht immer bekannt sind, auf die aber mit Hilfe von bekannten Beispielentit{\"a}ten geschlossen werden kann, so dass unbekannte Entit{\"a}ten extrahiert werden k{\"o}nnen. Die Bezeichner der anderen Klasse von Entit{\"a}ten haben eher umschreibenden Charakter. Die korrespondierenden Umschreibungen in Texten k{\"o}nnen variieren, wodurch eine Identifikation derartiger Entit{\"a}ten oft erschwert wird. Zur effizienteren Entwicklung von IE-Systemen wird in der Dissertation ein Verfahren untersucht, das alleine anhand von Beispielentit{\"a}ten effektive Regul{\"a}re Ausdr{\"u}cke zur Extraktion von unbekannten Entit{\"a}ten erlernt und damit den manuellen Aufwand in derartigen Anwendungsf{\"a}llen minimiert. Verschiedene Generalisierungs- und Spezialisierungsheuristiken erkennen Muster auf verschiedenen Abstraktionsebenen und schaffen dadurch einen Ausgleich zwischen Genauigkeit und Vollst{\"a}ndigkeit bei der Extraktion. Bekannte Regellernverfahren im Bereich der Informationsextraktion unterst{\"u}tzen die beschriebenen Problemstellungen nicht, sondern ben{\"o}tigen einen (annotierten) Dokumentenkorpus. Eine Methode zur Identifikation von Entit{\"a}ten, die durch Graph-strukturierte Referenzdaten vordefiniert sind, wird als dritter Schwerpunkt untersucht. Es werden Verfahren konzipiert, welche {\"u}ber einen exakten Zeichenkettenvergleich zwischen Text und Referenzdatensatz hinausgehen und Teil{\"u}bereinstimmungen und Beziehungen zwischen Entit{\"a}ten zur Identifikation und Disambiguierung heranziehen. Das in der Arbeit vorgestellte Verfahren ist bisherigen Ans{\"a}tzen hinsichtlich der Genauigkeit und Vollst{\"a}ndigkeit bei der Identifikation {\"u}berlegen.},
  language  = {de}
}
@phdthesis{Brueckner2012,
  author    = {Br{\"u}ckner, Michael},
  title     = {Prediction games : machine learning in the presence of an adversary},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-203-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60375},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 121},
  year      = {2012},
  abstract  = {In many applications one is faced with the problem of inferring some functional relation between input and output variables from given data. Consider, for instance, the task of email spam filtering where one seeks to find a model which automatically assigns new, previously unseen emails to class spam or non-spam. Building such a predictive model based on observed training inputs (e.g., emails) with corresponding outputs (e.g., spam labels) is a major goal of machine learning. Many learning methods assume that these training data are governed by the same distribution as the test data which the predictive model will be exposed to at application time. That assumption is violated when the test data are generated in response to the presence of a predictive model. This becomes apparent, for instance, in the above example of email spam filtering. Here, email service providers employ spam filters and spam senders engineer campaign templates such as to achieve a high rate of successful deliveries despite any filters. Most of the existing work casts such situations as learning robust models which are unsusceptible against small changes of the data generation process. The models are constructed under the worst-case assumption that these changes are performed such to produce the highest possible adverse effect on the performance of the predictive model. However, this approach is not capable to realistically model the true dependency between the model-building process and the process of generating future data. We therefore establish the concept of prediction games: We model the interaction between a learner, who builds the predictive model, and a data generator, who controls the process of data generation, as an one-shot game. The game-theoretic framework enables us to explicitly model the players' interests, their possible actions, their level of knowledge about each other, and the order at which they decide for an action. We model the players' interests as minimizing their own cost function which both depend on both players' actions. The learner's action is to choose the model parameters and the data generator's action is to perturbate the training data which reflects the modification of the data generation process with respect to the past data. We extensively study three instances of prediction games which differ regarding the order in which the players decide for their action. We first assume that both player choose their actions simultaneously, that is, without the knowledge of their opponent's decision. We identify conditions under which this Nash prediction game has a meaningful solution, that is, a unique Nash equilibrium, and derive algorithms that find the equilibrial prediction model. As a second case, we consider a data generator who is potentially fully informed about the move of the learner. This setting establishes a Stackelberg competition. We derive a relaxed optimization criterion to determine the solution of this game and show that this Stackelberg prediction game generalizes existing prediction models. Finally, we study the setting where the learner observes the data generator's action, that is, the (unlabeled) test data, before building the predictive model. As the test data and the training data may be governed by differing probability distributions, this scenario reduces to learning under covariate shift. We derive a new integrated as well as a two-stage method to account for this data set shift. In case studies on email spam filtering we empirically explore properties of all derived models as well as several existing baseline methods. We show that spam filters resulting from the Nash prediction game as well as the Stackelberg prediction game in the majority of cases outperform other existing baseline methods.},
  language  = {en}
}
@phdthesis{Bordihn2011,
  author    = {Bordihn, Henning},
  title     = {Contributions to the syntactical analysis beyond context-freeness},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59719},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Parsability approaches of several grammar formalisms generating also non-context-free languages are explored. Chomsky grammars, Lindenmayer systems, grammars with controlled derivations, and grammar systems are treated. Formal properties of these mechanisms are investigated, when they are used as language acceptors. Furthermore, cooperating distributed grammar systems are restricted so that efficient deterministic parsing without backtracking becomes possible. For this class of grammar systems, the parsing algorithm is presented and the feature of leftmost derivations is investigated in detail.},
  language  = {en}
}
@phdthesis{Boehm2013,
  author    = {B{\"o}hm, Christoph},
  title     = {Enriching the Web of Data with topics and links},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68624},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {This thesis presents novel ideas and research findings for the Web of Data - a global data space spanning many so-called Linked Open Data sources. Linked Open Data adheres to a set of simple principles to allow easy access and reuse for data published on the Web. Linked Open Data is by now an established concept and many (mostly academic) publishers adopted the principles building a powerful web of structured knowledge available to everybody. However, so far, Linked Open Data does not yet play a significant role among common web technologies that currently facilitate a high-standard Web experience. In this work, we thoroughly discuss the state-of-the-art for Linked Open Data and highlight several shortcomings - some of them we tackle in the main part of this work. First, we propose a novel type of data source meta-information, namely the topics of a dataset. This information could be published with dataset descriptions and support a variety of use cases, such as data source exploration and selection. For the topic retrieval, we present an approach coined Annotated Pattern Percolation (APP), which we evaluate with respect to topics extracted from Wikipedia portals. Second, we contribute to entity linking research by presenting an optimization model for joint entity linking, showing its hardness, and proposing three heuristics implemented in the LINked Data Alignment (LINDA) system. Our first solution can exploit multi-core machines, whereas the second and third approach are designed to run in a distributed shared-nothing environment. We discuss and evaluate the properties of our approaches leading to recommendations which algorithm to use in a specific scenario. The distributed algorithms are among the first of their kind, i.e., approaches for joint entity linking in a distributed fashion. Also, we illustrate that we can tackle the entity linking problem on the very large scale with data comprising more than 100 millions of entity representations from very many sources. Finally, we approach a sub-problem of entity linking, namely the alignment of concepts. We again target a method that looks at the data in its entirety and does not neglect existing relations. Also, this concept alignment method shall execute very fast to serve as a preprocessing for further computations. Our approach, called Holistic Concept Matching (HCM), achieves the required speed through grouping the input by comparing so-called knowledge representations. Within the groups, we perform complex similarity computations, relation conclusions, and detect semantic contradictions. The quality of our result is again evaluated on a large and heterogeneous dataset from the real Web. In summary, this work contributes a set of techniques for enhancing the current state of the Web of Data. All approaches have been tested on large and heterogeneous real-world input.},
  language  = {en}
}
@phdthesis{Sawade2012,
  author    = {Sawade, Christoph},
  title     = {Active evaluation of predictive models},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-255-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65583},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 157},
  year      = {2012},
  abstract  = {The field of machine learning studies algorithms that infer predictive models from data. Predictive models are applicable for many practical tasks such as spam filtering, face and handwritten digit recognition, and personalized product recommendation. In general, they are used to predict a target label for a given data instance. In order to make an informed decision about the deployment of a predictive model, it is crucial to know the model's approximate performance. To evaluate performance, a set of labeled test instances is required that is drawn from the distribution the model will be exposed to at application time. In many practical scenarios, unlabeled test instances are readily available, but the process of labeling them can be a time- and cost-intensive task and may involve a human expert. This thesis addresses the problem of evaluating a given predictive model accurately with minimal labeling effort. We study an active model evaluation process that selects certain instances of the data according to an instrumental sampling distribution and queries their labels. We derive sampling distributions that minimize estimation error with respect to different performance measures such as error rate, mean squared error, and F-measures. An analysis of the distribution that governs the estimator leads to confidence intervals, which indicate how precise the error estimation is. Labeling costs may vary across different instances depending on certain characteristics of the data. For instance, documents differ in their length, comprehensibility, and technical requirements; these attributes affect the time a human labeler needs to judge relevance or to assign topics. To address this, the sampling distribution is extended to incorporate instance-specific costs. We empirically study conditions under which the active evaluation processes are more accurate than a standard estimate that draws equally many instances from the test distribution. We also address the problem of comparing the risks of two predictive models. The standard approach would be to draw instances according to the test distribution, label the selected instances, and apply statistical tests to identify significant differences. Drawing instances according to an instrumental distribution affects the power of a statistical test. We derive a sampling procedure that maximizes test power when used to select instances, and thereby minimizes the likelihood of choosing the inferior model. Furthermore, we investigate the task of comparing several alternative models; the objective of an evaluation could be to rank the models according to the risk that they incur or to identify the model with lowest risk. An experimental study shows that the active procedure leads to higher test power than the standard test in many application domains. Finally, we study the problem of evaluating the performance of ranking functions, which are used for example for web search. In practice, ranking performance is estimated by applying a given ranking model to a representative set of test queries and manually assessing the relevance of all retrieved items for each query. We apply the concepts of active evaluation and active comparison to ranking functions and derive optimal sampling distributions for the commonly used performance measures Discounted Cumulative Gain and Expected Reciprocal Rank. Experiments on web search engine data illustrate significant reductions in labeling costs.},
  language  = {en}
}