@inproceedings{ZwicklbauerSeifertGranitzer2016, author = {Zwicklbauer, Stefan and Seifert, Christin and Granitzer, Michael}, title = {Robust and Collective Entity Disambiguation through Semantic Embeddings}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-3704}, year = {2016}, abstract = {Entity disambiguation is the task of mapping ambiguous terms in natural-language text to its entities in a knowledge base. It finds its application in the extraction of structured data in RDF (Resource Description Framework) from textual documents, but equally so in facilitating artificial intelligence applications, such as Semantic Search, Reasoning and Question \& Answering. We propose a new collective, graph-based disambiguation algorithm utilizing semantic entity and document embeddings for robust entity disambiguation. Robust thereby refers to the property of achieving better than state-of-the-art results over a wide range of very different data sets. Our approach is also able to abstain if no appropriate entity can be found for a specific surface form. Our evaluation shows, that our approach achieves significantly (>5\%) better results than all other publicly available disambiguation algorithms on 7 of 9 datasets without data set specific tuning. Moreover, we discuss the influence of the quality of the knowledge base on the disambiguation accuracy and indicate that our algorithm achieves better results than non-publicly available state-of-the-art algorithms.}, language = {en} } @unpublished{ZwicklbauerSeifertGranitzer2016, author = {Zwicklbauer, Stefan and Seifert, Christin and Granitzer, Michael}, title = {DoSeR - A Knowledge-Base-Agnostic Framework for Entity Disambiguation Using Semantic Embeddings}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-3670}, year = {2016}, abstract = {Entity disambiguation is the task of mapping ambiguous terms in natural-language text to its entities in a knowledge base. It finds its application in the extraction of structured data in RDF (Resource Description Framework) from textual documents, but equally so in facilitating artificial intelligence applications, such as Semantic Search, Reasoning and Question \& Answering. In this work, we propose DoSeR (Disambiguation of Semantic Resources), a (named) entity disambiguation framework that is knowledge-base-agnostic in terms of RDF (e.g. DBpedia) and entity-annotated document knowledge bases (e.g. Wikipedia). Initially, our framework automatically generates semantic entity embeddings given one or multiple knowledge bases. In the following, DoSeR accepts documents with a given set of surface forms as input and collectively links them to an entity in a knowledge base with a graph-based approach. We evaluate DoSeR on seven different data sets against publicly available, state-of-the-art (named) entity disambiguation frameworks. Our approach outperforms the state-of-the-art approaches that make use of RDF knowledge bases and/or entity-annotated document knowledge bases by up to 10\% F1 measure.}, language = {de} } @phdthesis{Zwicklbauer2017, author = {Zwicklbauer, Stefan}, title = {Robust Entity Linking in Heterogeneous Domains}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-5047}, school = {Universit{\"a}t Passau}, pages = {iv, 191 Seiten}, year = {2017}, abstract = {Entity Linking is the task of mapping terms in arbitrary documents to entities in a knowledge base by identifying the correct semantic meaning. It is applied in the extraction of structured data in RDF (Resource Description Framework) from textual documents, but equally so in facilitating artificial intelligence applications, such as Semantic Search, Reasoning and Question and Answering. Most existing Entity Linking systems were optimized for specific domains (e.g., general domain, biomedical domain), knowledge base types (e.g., DBpedia, Wikipedia), or document structures (e.g., tables) and types (e.g., news articles, tweets). This led to very specialized systems that lack robustness and are only applicable for very specific tasks. In this regard, this work focuses on the research and development of a robust Entity Linking system in terms of domains, knowledge base types, and document structures and types. To create a robust Entity Linking system, we first analyze the following three crucial components of an Entity Linking algorithm in terms of robustness criteria: (i) the underlying knowledge base, (ii) the entity relatedness measure, and (iii) the textual context matching technique. Based on the analyzed components, our scientific contributions are three-fold. First, we show that a federated approach leveraging knowledge from various knowledge base types can significantly improve robustness in Entity Linking systems. Second, we propose a new state-of-the-art, robust entity relatedness measure for topical coherence computation based on semantic entity embeddings. Third, we present the neural-network-based approach Doc2Vec as a textual context matching technique for robust Entity Linking. Based on our previous findings and outcomes, our main contribution in this work is DoSeR (Disambiguation of Semantic Resources). DoSeR is a robust, knowledge-base-agnostic Entity Linking framework that extracts relevant entity information from multiple knowledge bases in a fully automatic way. The integrated algorithm represents a collective, graph-based approach that utilizes semantic entity and document embeddings for entity relatedness and textual context matching computation. Our evaluation shows, that DoSeR achieves state-of-the-art results over a wide range of different document structures (e.g., tables), document types (e.g., news documents) and domains (e.g., general domain, biomedical domain). In this context, DoSeR outperforms all other (publicly available) Entity Linking algorithms on most data sets.}, subject = {Linked Data}, language = {en} }