Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 14 of 14 for “"LARGE KNOWLEDGE BASES"”.
-
Mining software repositories to support software evolution
… software maintenance activities. Given the often large amounts of information stored in these repositories, researchers have proposed to mine and analyze these large knowledge bases in order to study and support various aspects of the evolution of a software system. In this thesis, we introduce a …
-
A Turing Game for commonsense knowledge extraction
… of the field. Traditionally, commonsense knowledge is gathered by using humans to create and insert it in knowledge bases. Automating the collection of commonsense from text that is freely available can reduce the cost and effort of creating large knowledge bases and can enable systems …
-
A Formalism for Visual Query Interface Design
The massive volumes and the huge variety of large knowledge bases make information exploration and analysis difficult. An important activity is data filtering and selection, in which both querying and visualization play important roles. Interfaces for data exploration environments normally include …
-
Informative web content guidelines: A practitioner model for online content effectiveness
… the world wide web, many organisations publish large knowledge bases as online informative content, enabling access for their current and potential stakeholders, customers, and service users. Providing universal access to information is a key feature of many national laws, ensuring that content …
-
A Behavioral Theory Perspective on Acquisitions, Acquisition Performance, and Strategic Alternatives
… on 2,502 acquisitions that were conducted by 87 large US information and communication technology (ICT) companies from 1990 to 2010. The first essay concentrates on the behavioral consequences of performance deviations by simultaneously studying firm engagement in two polar types of strategic …
-
Uncertainty management for description logic-based ontologies
… representation and reasoning of the uncertainty knowledge, query optimization in this context has received little attention. In this thesis, we tackle this problem in both theoretical and practical aspects by taking a generic approach. We first propose the [Special characters omitted.] framework …
-
Incremental knowledge acquisition for natural language processing
… methods. In supervised learning approaches, a large annotated training corpus is required for the learning algorithms to achieve decent results. However, annotated corpora are expensive to obtain and usually available only for established tasks. Unsupervised learning approaches usually start …
-
A parallel process model and architecture for a Pure Logic Language
… parallel logic systems for the implementation of large knowledge bases. The thesis describes proposals for a parallel logic system based on a new logic programming language, the Pure Logic Language. The work has involved the definition and implementation of a new logic interpreter which …
-
Massively parallel reasoning in transitive relationship hierarchies
This research focuses on building a parallel knowledge representation and reasoning system for the purpose of making progress in realizing human-like intelligence. To achieve human-like intelligence, it is necessary to model human reasoning processes by programs. Knowledge in the real world is huge …
-
Explainable Multi-Step Reasoning Over Natural Language
… problems require the retrieval of evidence from large knowledge bases, while neither traditional information retrieval (IR) methods nor neural IR methods yield satisfactory results. Second, neural language models are largely black boxes, and how the language models solve the multi-step reasoning …
-
Beyond Labels and Captions: Contextualizing Grounded Semantics for Explainable Visual Interpretation
… ground evidence in the image. Hence, the learned knowledge is limited to the annotated training set. An open world, on the other hand, does not assume the distribution of semantics and requires generalization beyond the training annotations. Increasingly complex models require massive amounts of …
-
Tensor factorization for relational learning
… In the second part of the thesis, we focus on large-scale relational learning and its applications to Linked Data. By exploiting the inherent sparsity of relational data, an efficient computation of RESCAL can scale up to the size of large knowledge bases, consisting of millions of entities, …
-
ΤΜΗΜΑΤΟΠΟΙΗΜΕΝΕΣ ΒΑΣΕΙΣ ΓΝΩΣΗΣ ΣΕ ΤΟΠΙΚΑ ΔΙΚΤΥΑ ΜΙΚΡΟΥΠΟΛΟΓΙΣΤΩΝ
ΣΤΗ ΔΙΑΤΡΙΒΗ ΠΡΟΤΕΙΝΕΤΑΙ ΜΙΑ ΝΕΑ ΔΟΜΗ ΠΟΥ ΔΙΝΕΙ ΤΗ ΔΥΝΑΤΟΤΗΤΑ ΔΙΑΧΕΙΡΙΣΗΣ ΒΑΣΕΩΝ ΓΝΩΣΗΣ ΣΕ ΤΟΠΙΚΑ ΔΙΚΤΥΑ ΜΙΚΡΟΥΠΟΛΟΓΙΣΤΩΝ. Η ΔΙΑΤΡΙΒΗ ΣΑΝ ΚΥΡΙΟ ΣΤΟΧΟ ΕΧΕΙ ΤΑ ΣΥΝΕΡΓΑΖΟΜΕΝΑ ΣΥΣΤΗΜΑΤΑ ΔΕΔΟΜΕΝΩΝ ΚΑΙ ΓΝΩΣΗΣ ΣΕ ΕΠΙΠΕΔΟ ΚΥΡΙΑΣ ΜΝΗΜΗΣ ΚΑΙ ΑΠΟΤΕΛΕΙΤΑΙ ΑΠΟ ΠΕΝΤΑ ΚΕΦΑΛΑΙΑ ΚΑΙ ΕΝΑ ΠΑΡΑΡΤΗΜΑ. ΣΤΟ 1Ο ΚΕΦΑΛΑΙΟ …