With the ever increase in biomedical literature, text-mining has emerged as an important technology to support bio-curation and search. Word sense disambiguation (WSD), the correct identification of terms in text in the light of ambiguity, is an important problem in text-mining. Since the late 1940s many approaches based on supervised (decision trees, naive Bayes, neural networks, support vector machines) and unsupervised machine learning (context-clustering, word-clustering, co-occurrence graphs) have been developed. Knowledge-based methods that make use of the WordNet computational lexicon have also been developed. But only few make use of ontologies, i.e. hierarchical controlled vocabularies, to solve the problem and none exploit inference over ontologies and the use of metadata from publications. This thesis addresses the WSD problem in biomedical ontologies by suggesting different approaches for word sense disambiguation that use ontologies and metadata. The "Closest Sense" method assumes that the ontology defines multiple senses of the term; it computes the shortest path of co-occurring terms in the document to one of these senses. The "Term Cooc" method defines a log-odds ratio for co-occurring terms including inferred co-occurrences. The "MetaData" approach trains a classifier on metadata; it does not require any ontology, but requires training data, which the other methods do not. These approaches are compared to each other when applied to a manually curated training corpus of 2600 documents for seven ambiguous terms from the Gene Ontology and MeSH. All approaches over all conditions achieve 80% success rate on average. The MetaData approach performs best with 96%, when trained on high-quality data. Its performance deteriorates as quality of the training data decreases. The Term Cooc approach performs better on Gene Ontology (92% success) than on MeSH (73% success) as MeSH is not a strict is-a/part-of, but rather a loose is-related-to hierarchy. The Closest Sense approach achieves on average 80% success rate. Furthermore, the thesis showcases applications ranging from ontology design to semantic search where WSD is important.

Since the proposal of hypertext by Tim Berners-Lee to his employer CERN on March 12, 1989 the World Wide Web has grown to more than one billion Web pages and still grows. With the later proposed Semantic Web vision,Berners-Lee et al. suggested an extension of the existing (Document) Web to allow better reuse, sharing and understanding of data. Both the Document Web and the Web of Data (which is the current implementation of the Semantic Web) grow continuously. This is a mixed blessing, as the two forms of the Web grow concurrently and most commonly contain different pieces of information. Modern information systems must thus bridge a Semantic Gap to allow a holistic and unified access to information about a particular information independent of the representation of the data. One way to bridge the gap between the two forms of the Web is the extraction of structured data, i.e., RDF, from the growing amount of unstructured and semi-structured information (e.g., tables and XML) on the Document Web. Note, that unstructured data stands for any type of textual information like news, blogs or tweets. While extracting structured data from unstructured data allows the development of powerful information system, it requires high-quality and scalable knowledge extraction frameworks to lead to useful results. The dire need for such approaches has led to the development of a multitude of annotation frameworks and tools. However, most of these approaches are not evaluated on the same datasets or using the same measures. The resulting Evaluation Gap needs to be tackled by a concise evaluation framework to foster fine-grained and uniform evaluations of annotation tools and frameworks over any knowledge bases. Moreover, with the constant growth of data and the ongoing decentralization of knowledge, intuitive ways for non-experts to access the generated data are required. Humans adapted their search behavior to current Web data by access paradigms such as keyword search so as to retrieve high-quality results. Hence, most Web users only expect Web documents in return. However, humans think and most commonly express their information needs in their natural language rather than using keyword phrases. Answering complex information needs often requires the combination of knowledge from various, differently structured data sources. Thus, we observe an Information Gap between natural-language questions and current keyword-based search paradigms, which in addition do not make use of the available structured and unstructured data sources. Question Answering (QA) systems provide an easy and efficient way to bridge this gap by allowing to query data via natural language, thus reducing (1) a possible loss of precision and (2) potential loss of time while reformulating the search intention to transform it into a machine-readable way. Furthermore, QA systems enable answering natural language queries with concise results instead of links to verbose Web documents. Additionally, they allow as well as encourage the access to and the combination of knowledge from heterogeneous knowledge bases (KBs) within one answer. Consequently, three main research gaps are considered and addressed in this work: First, addressing the Semantic Gap between the unstructured Document Web and the Semantic Gap requires the development of scalable and accurate approaches for the extraction of structured data in RDF. This research challenge is addressed by several approaches within this thesis. This thesis presents CETUS, an approach for recognizing entity types to populate RDF KBs. Furthermore, our knowledge base-agnostic disambiguation framework AGDISTIS can efficiently detect the correct URIs for a given set of named entities. Additionally, we introduce REX, a Web-scale framework for RDF extraction from semi-structured (i.e., templated) websites which makes use of the semantics of the reference knowledge based to check the extracted data. The ongoing research on closing the Semantic Gap has already yielded a large number of annotation tools and frameworks. However, these approaches are currently still hard to compare since the published evaluation results are calculated on diverse datasets and evaluated based on different measures. On the other hand, the issue of comparability of results is not to be regarded as being intrinsic to the annotation task. Indeed, it is now well established that scientists spend between 60% and 80% of their time preparing data for experiments. Data preparation being such a tedious problem in the annotation domain is mostly due to the different formats of the gold standards as well as the different data representations across reference datasets. We tackle the resulting Evaluation Gap in two ways: First, we introduce a collection of three novel datasets, dubbed N3, to leverage the possibility of optimizing NER and NED algorithms via Linked Data and to ensure a maximal interoperability to overcome the need for corpus-specific parsers. Second, we present GERBIL, an evaluation framework for semantic entity annotation. The rationale behind our framework is to provide developers, end users and researchers with easy-to-use interfaces that allow for the agile, fine-grained and uniform evaluation of annotation tools and frameworks on multiple datasets. The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Moreover, the increasing the demand for natural-language interfaces as depicted by current mobile applications requires systems to deeply understand the underlying user information need. In conclusion, the natural language interface for asking questions requires a hybrid approach to data usage, i.e., simultaneously performing a search on full-texts and semantic knowledge bases. To close the Information Gap, this thesis presents HAWK, a novel entity search approach developed for hybrid QA based on combining structured RDF and unstructured full-text data sources.

Der Einfluss sogenannter nutzergenerierter Inhalte im Web hat in den letzten Jahren stetig zugenommen. Auf Plattformen wie Blogs, sozialen Netzwerken oder Medienportalen werden durch Anwender kontinuierlich Textnachrichten, Bilder oder Videos publiziert. Auch Inhalte, die aktuelle gesellschaftliche Ereignisse, wie beispielsweise den Euromaidan in Kiew dokumentieren, werden durch diese Plattformen verbreitet. Nutzergenerierte Inhalte bieten folglich das Potential, zusätzliche Hintergrundinformationen über Ereignisse direkt vom Ort des Geschehens zu liefern. Diese Arbeit verfolgt die Vision einer Nachrichtenplattform, die unter Verwendung von Methoden des Information Retrievals und der Informationsextraktion Nachrichtenereignisse erkennt, diese automatisiert mit relevanten nutzergenerierten Inhalten anreichert und dem Leser präsentiert. Zur Suche nutzergenerierter Inhalte kommen in dieser Arbeit maßgeblich geographische Entitäten, also Ortsbezeichnungen zum Einsatz. Für die Extraktion dieser Entitäten aus gegebenen Nachrichtendokumenten stellt die Arbeit verschiedene neue Methoden vor. Die Entitäten werden genutzt, um zielgerichtete Suchanfragen zu erzeugen. Es wird gezeigt, dass sich eine geounterstützte Suche für das Auffinden nutzergenerierter Inhalte besser eignet als eine konventionelle schlüsselwortbasierte Suche.

With the ever increase in biomedical literature, text-mining has emerged as an important technology to support bio-curation and search. Word sense disambiguation (WSD), the correct identification of terms in text in the light of ambiguity, is an important problem in text-mining. Since the late 1940s many approaches based on supervised (decision trees, naive Bayes, neural networks, support vector machines) and unsupervised machine learning (context-clustering, word-clustering, co-occurrence graphs) have been developed. Knowledge-based methods that make use of the WordNet computational lexicon have also been developed. But only few make use of ontologies, i.e. hierarchical controlled vocabularies, to solve the problem and none exploit inference over ontologies and the use of metadata from publications. This thesis addresses the WSD problem in biomedical ontologies by suggesting different approaches for word sense disambiguation that use ontologies and metadata. The "Closest Sense" method assumes that the ontology defines multiple senses of the term; it computes the shortest path of co-occurring terms in the document to one of these senses. The "Term Cooc" method defines a log-odds ratio for co-occurring terms including inferred co-occurrences. The "MetaData" approach trains a classifier on metadata; it does not require any ontology, but requires training data, which the other methods do not. These approaches are compared to each other when applied to a manually curated training corpus of 2600 documents for seven ambiguous terms from the Gene Ontology and MeSH. All approaches over all conditions achieve 80% success rate on average. The MetaData approach performs best with 96%, when trained on high-quality data. Its performance deteriorates as quality of the training data decreases. The Term Cooc approach performs better on Gene Ontology (92% success) than on MeSH (73% success) as MeSH is not a strict is-a/part-of, but rather a loose is-related-to hierarchy. The Closest Sense approach achieves on average 80% success rate. Furthermore, the thesis showcases applications ranging from ontology design to semantic search where WSD is important.