This thesis is a compendium of scientific works and engineering specifications that have been contributed to a large community of stakeholders to be copied, adapted, mixed, built upon and exploited in any way possible to achieve a common goal: Integrating Natural Language Processing (NLP) and Language Resources Using Linked Data The explosion of information technology in the last two decades has led to a substantial growth in quantity, diversity and complexity of web-accessible linguistic data. These resources become even more useful when linked with each other and the last few years have seen the emergence of numerous approaches in various disciplines concerned with linguistic resources and NLP tools. It is the challenge of our time to store, interlink and exploit this wealth of data accumulated in more than half a century of computational linguistics, of empirical, corpus-based study of language, and of computational lexicography in all its heterogeneity. The vision of the Giant Global Graph (GGG) was conceived by Tim Berners-Lee aiming at connecting all data on the Web and allowing to discover new relations between this openly-accessible data. This vision has been pursued by the Linked Open Data (LOD) community, where the cloud of published datasets comprises 295 data repositories and more than 30 billion RDF triples (as of September 2011). RDF is based on globally unique and accessible URIs and it was specifically designed to establish links between such URIs (or resources). This is captured in the Linked Data paradigm that postulates four rules: (1) Referred entities should be designated by URIs, (2) these URIs should be resolvable over HTTP, (3) data should be represented by means of standards such as RDF, (4) and a resource should include links to other resources. Although it is difficult to precisely identify the reasons for the success of the LOD effort, advocates generally argue that open licenses as well as open access are key enablers for the growth of such a network as they provide a strong incentive for collaboration and contribution by third parties. In his keynote at BNCOD 2011, Chris Bizer argued that with RDF the overall data integration effort can be “split between data publishers, third parties, and the data consumer”, a claim that can be substantiated by observing the evolution of many large data sets constituting the LOD cloud. As written in the acknowledgement section, parts of this thesis has received numerous feedback from other scientists, practitioners and industry in many different ways. The main contributions of this thesis are summarized here: Part I – Introduction and Background. During his keynote at the Language Resource and Evaluation Conference in 2012, Sören Auer stressed the decentralized, collaborative, interlinked and interoperable nature of the Web of Data. The keynote provides strong evidence that Semantic Web technologies such as Linked Data are on its way to become main stream for the representation of language resources. The jointly written companion publication for the keynote was later extended as a book chapter in The People’s Web Meets NLP and serves as the basis for “Introduction” and “Background”, outlining some stages of the Linked Data publication and refinement chain. Both chapters stress the importance of open licenses and open access as an enabler for collaboration, the ability to interlink data on the Web as a key feature of RDF as well as provide a discussion about scalability issues and decentralization. Furthermore, we elaborate on how conceptual interoperability can be achieved by (1) re-using vocabularies, (2) agile ontology development, (3) meetings to refine and adapt ontologies and (4) tool support to enrich ontologies and match schemata. Part II - Language Resources as Linked Data. “Linked Data in Linguistics” and “NLP & DBpedia, an Upward Knowledge Acquisition Spiral” summarize the results of the Linked Data in Linguistics (LDL) Workshop in 2012 and the NLP & DBpedia Workshop in 2013 and give a preview of the MLOD special issue. In total, five proceedings – three published at CEUR (OKCon 2011, WoLE 2012, NLP & DBpedia 2013), one Springer book (Linked Data in Linguistics, LDL 2012) and one journal special issue (Multilingual Linked Open Data, MLOD to appear) – have been (co-)edited to create incentives for scientists to convert and publish Linked Data and thus to contribute open and/or linguistic data to the LOD cloud. Based on the disseminated call for papers, 152 authors contributed one or more accepted submissions to our venues and 120 reviewers were involved in peer-reviewing. “DBpedia as a Multilingual Language Resource” and “Leveraging the Crowdsourcing of Lexical Resources for Bootstrapping a Linguistic Linked Data Cloud” contain this thesis’ contribution to the DBpedia Project in order to further increase the size and inter-linkage of the LOD Cloud with lexical-semantic resources. Our contribution comprises extracted data from Wiktionary (an online, collaborative dictionary similar to Wikipedia) in more than four languages (now six) as well as language-specific versions of DBpedia, including a quality assessment of inter-language links between Wikipedia editions and internationalized content negotiation rules for Linked Data. In particular the work described in created the foundation for a DBpedia Internationalisation Committee with members from over 15 different languages with the common goal to push DBpedia as a free and open multilingual language resource. Part III - The NLP Interchange Format (NIF). “NIF 2.0 Core Specification”, “NIF 2.0 Resources and Architecture” and “Evaluation and Related Work” constitute one of the main contribution of this thesis. The NLP Interchange Format (NIF) is an RDF/OWL-based format that aims to achieve interoperability between Natural Language Processing (NLP) tools, language resources and annotations. The core specification is included in and describes which URI schemes and RDF vocabularies must be used for (parts of) natural language texts and annotations in order to create an RDF/OWL-based interoperability layer with NIF built upon Unicode Code Points in Normal Form C. In , classes and properties of the NIF Core Ontology are described to formally define the relations between text, substrings and their URI schemes. contains the evaluation of NIF. In a questionnaire, we asked questions to 13 developers using NIF. UIMA, GATE and Stanbol are extensible NLP frameworks and NIF was not yet able to provide off-the-shelf NLP domain ontologies for all possible domains, but only for the plugins used in this study. After inspecting the software, the developers agreed however that NIF is adequate enough to provide a generic RDF output based on NIF using literal objects for annotations. All developers were able to map the internal data structure to NIF URIs to serialize RDF output (Adequacy). The development effort in hours (ranging between 3 and 40 hours) as well as the number of code lines (ranging between 110 and 445) suggest, that the implementation of NIF wrappers is easy and fast for an average developer. Furthermore the evaluation contains a comparison to other formats and an evaluation of the available URI schemes for web annotation. In order to collect input from the wide group of stakeholders, a total of 16 presentations were given with extensive discussions and feedback, which has lead to a constant improvement of NIF from 2010 until 2013. After the release of NIF (Version 1.0) in November 2011, a total of 32 vocabulary employments and implementations for different NLP tools and converters were reported (8 by the (co-)authors, including Wiki-link corpus, 13 by people participating in our survey and 11 more, of which we have heard). Several roll-out meetings and tutorials were held (e.g. in Leipzig and Prague in 2013) and are planned (e.g. at LREC 2014). Part IV - The NLP Interchange Format in Use. “Use Cases and Applications for NIF” and “Publication of Corpora using NIF” describe 8 concrete instances where NIF has been successfully used. One major contribution in is the usage of NIF as the recommended RDF mapping in the Internationalization Tag Set (ITS) 2.0 W3C standard and the conversion algorithms from ITS to NIF and back. One outcome of the discussions in the standardization meetings and telephone conferences for ITS 2.0 resulted in the conclusion there was no alternative RDF format or vocabulary other than NIF with the required features to fulfill the working group charter. Five further uses of NIF are described for the Ontology of Linguistic Annotations (OLiA), the RDFaCE tool, the Tiger Corpus Navigator, the OntosFeeder and visualisations of NIF using the RelFinder tool. These 8 instances provide an implemented proof-of-concept of the features of NIF. starts with describing the conversion and hosting of the huge Google Wikilinks corpus with 40 million annotations for 3 million web sites. The resulting RDF dump contains 477 million triples in a 5.6 GB compressed dump file in turtle syntax. describes how NIF can be used to publish extracted facts from news feeds in the RDFLiveNews tool as Linked Data. Part V - Conclusions. provides lessons learned for NIF, conclusions and an outlook on future work. Most of the contributions are already summarized above. One particular aspect worth mentioning is the increasing number of NIF-formated corpora for Named Entity Recognition (NER) that have come into existence after the publication of the main NIF paper Integrating NLP using Linked Data at ISWC 2013. These include the corpora converted by Steinmetz, Knuth and Sack for the NLP & DBpedia workshop and an OpenNLP-based CoNLL converter by Brümmer. Furthermore, we are aware of three LREC 2014 submissions that leverage NIF: NIF4OGGD - NLP Interchange Format for Open German Governmental Data, N^3 – A Collection of Datasets for Named Entity Recognition and Disambiguation in the NLP Interchange Format and Global Intelligent Content: Active Curation of Language Resources using Linked Data as well as an early implementation of a GATE-based NER/NEL evaluation framework by Dojchinovski and Kliegr. Further funding for the maintenance, interlinking and publication of Linguistic Linked Data as well as support and improvements of NIF is available via the expiring LOD2 EU project, as well as the CSA EU project called LIDER, which started in November 2013. Based on the evidence of successful adoption presented in this thesis, we can expect a decent to high chance of reaching critical mass of Linked Data technology as well as the NIF standard in the field of Natural Language Processing and Language Resources.

In der akademischen Fachliteratur existieren kaum Forschungsergebnisse zu One-to-One-Marketing, die auf Anwendungen im Einzelhandel ausgerichtet sind. Zu den Hauptgründen zählen, dass Ansätze nicht auf die Größe typischer Einzelhandelsanwendungen skalieren und dass die Datenverfügbarkeit auf Händler und Marketing-Systemanbieter beschränkt ist. Die vorliegende Dissertation entwickelt neue deskriptive, prädiktive und präskriptive Modelle für automatisiertes Target Marketing, die auf Representation Learning und Deep Learning basieren, und untersucht deren Wirksamkeit in Praxisanwendungen. Im ersten Schritt zeigt die Arbeit, dass Representation Learning in der Lage ist, skalierbar Marktstrukturen zu analysieren. Der vorgeschlagene Ansatz zur Visualisierung von Marktstrukturen ist vollständig automatisiert und existierenden Methoden überlegen. Die Arbeit entwickelt anschließend ein skalierbares, nichtparametrisches Modell, das Produktwahl auf Konsumentenebene für alle Produkte im Sortiment großer Einzelhändler vorhersagt. Das Deep Neural Network übertrifft die Vorhersagekraft existierender Benchmarks und auf Basis des Modells abgeleitete Coupons erzielen signifikant höhere Umsatzsteigerungen. Die Dissertation untersucht abschließend eine Coupon-Engine, die auf den entwickelten Modellen basiert. Der Vergleich personalisierter Werbeaktionen mit Massenmarketing belegt, dass One-to-One Marketing Einlösungsraten, Umsätze und Gewinne steigern kann. Eine Analyse der Kundenreaktionen auf personalisierte Coupons im Rahmen eines Kundenbindungsprogrammes zeigt, dass personalisiertes Marketing Systemnutzung erhöht. Dies illustriert, wie Target Marketing und Kundenbindungsprogramme effizient kombiniert werden können. Die vorliegende Dissertation ist somit sowohl für Forscher als auch für Praktiker relevant. Neben leistungsfähigeren Modellansätzen bietet diese Arbeit relevante Implikationen für effizientes Promotion-Management und One-to-One-Marketing im Einzelhandel. / Research on one-to-one marketing with a focus on retailing is scarce in academic literature. The two main reasons are that the target marketing approaches proposed by researchers do not scale to the size of typical retail applications and that data regarding one-to-one marketing remain locked within retailers and marketing solution providers. This dissertation develops new descriptive, predictive, and prescriptive marketing models for automated target marketing that are based on representation learning and deep learning and studies the models’ impact in real-life applications. First, this thesis shows that representation learning is capable of analyzing market structures at scale. The proposed approach to visualizing market structures is fully automated and superior to existing mapping methods that are based on the same input data. The thesis then proposes a scalable, nonparametric model that predicts product choice for the entire assortment of a large retailer. The deep neural network outperforms benchmark methods for predicting customer purchases. Coupon policies based on the proposed model lead to substantially higher revenue lifts than policies based on the benchmark models. The remainder of the thesis studies a real-time offer engine that is based on the proposed models. The comparison of personalized promotions to non-targeted promotions shows that one-to-one marketing increases redemption rates, revenues, and profits. A study of customer responses to personalized price promotions within the retailer’s loyalty program reveals that personalized marketing also increases loyalty program usage. This illustrates how targeted price promotions can be integrated smoothly into loyalty programs. In summary, this thesis is highly relevant for both researchers and practitioners. The new deep learning models facilitate more scalable and efficient one-to-one marketing. In addition, this research offers pertinent implications for promotion management and one-to-one marketing.

Normalformen drücken semantische Eigenschaften einer Logik durch syntaktische Restriktionen aus. Sie ermöglichen es Algorithmen, Grenzen der Ausdrucksstärke einer Logik auszunutzen. Ein Beispiel ist die Lokalität der Logik erster Stufe (FO), die impliziert, dass Graph-Eigenschaften wie Erreichbarkeit oder Zusammenhang nicht FO-definierbar sind. Gaifman-Normalformen drücken die Bedeutung einer FO-Formel als Boolesche Kombination lokaler Eigenschaften aus. Sie haben eine wichtige Rolle in Model-Checking Algorithmen für Klassen dünn besetzter Graphen, deren Laufzeit durch die Größe der auszuwertenden Formel parametrisiert ist. Es ist jedoch bekannt, dass Gaifman-Normalformen im Allgemeinen nur mit nicht-elementarem Aufwand konstruiert werden können. Dies führt zu einer enormen Parameterabhängigkeit der genannten Algorithmen. Ähnliche nicht-elementare untere Schranken sind auch für Feferman-Vaught-Zerlegungen und für die Erhaltungssätze von Lyndon, Łoś und Tarski bekannt. Diese Arbeit untersucht die Komplexität der genannten Normalformen auf Klassen von Strukturen beschränkten Grades, für welche die nicht-elementaren unteren Schranken nicht gelten. Für diese Einschränkung werden Algorithmen mit elementarer Laufzeit für die Konstruktion von Gaifman-Normalformen, Feferman-Vaught-Zerlegungen, und für die Erhaltungssätze von Lyndon, Łoś und Tarski entwickelt, die in den ersten beiden Fällen worst-case optimal sind. Wichtig hierfür sind Hanf-Normalformen. Es wird gezeigt, dass eine Erweiterung von FO durch unäre Zählquantoren genau dann Hanf-Normalformen erlaubt, wenn alle Zählquantoren ultimativ periodisch sind, und wie Hanf-Normalformen in diesen Fällen in elementarer und worst-case optimaler Zeit konstruiert werden können. Dies führt zu Model-Checking Algorithmen für solche Erweiterungen von FO sowie zu Verallgemeinerungen der Algorithmen für Feferman-Vaught-Zerlegungen und die Erhaltungssätze von Lyndon, Łoś und Tarski. / Normal forms express semantic properties of logics by means of syntactical restrictions. They allow algorithms to benefit from restrictions of the expressive power of a logic. An example is the locality of first-order logic (FO), which implies that properties like reachability or connectivity cannot be defined in FO. Gaifman's local normal form expresses the satisfaction conditions of an FO-formula by a Boolean combination of local statements. Gaifman normal form serves as a first step in fixed-parameter model-checking algorithms, parameterised by the size of the formula, on sparse graph classes. However, it is known that in general, there are non-elementary lower bounds for the costs involved in transforming a formula into Gaifman normal form. This leads to an enormous parameter-dependency of the aforementioned algorithms. Similar non-elementary lower bounds also hold for Feferman-Vaught decompositions and for the preservation theorems by Lyndon, Łoś, and Tarski. This thesis investigates the complexity of these normal forms when restricting attention to classes of structures of bounded degree, for which the non-elementary lower bounds are known to fail. Under this restriction, the thesis provides algorithms with elementary and even worst-case optimal running time for the construction of Gaifman normal form and Feferman-Vaught decompositions. For the preservation theorems, algorithmic versions with elementary running time and non-matching lower bounds are provided. Crucial for these results is the notion of Hanf normal form. It is shown that an extension of FO by unary counting quantifiers allows Hanf normal forms if, and only if, all quantifiers are ultimately periodic, and furthermore, how Hanf normal form can be computed in elementary and worst-case optimal time in these cases. This leads to model-checking algorithms for such extensions of FO and also allows generalisations of the constructions for Feferman-Vaught decompositions and preservation theorems.