In this paper, we describe our approach to estimating the geographic location of videos. Our system relies on textual meta-data and includes two basic term filtering strategies: filtering according to the general use of terms and filtering according to the geographic spread. Combining both filtering steps yields 50% accuracy within a 10km range.

Huge amounts of digital videos are being produced and broadcast every day, leading to giant media archives. Effective techniques are needed to make such data accessible further. Automatic meta-data labelling of broadcast media is an essential task for multimedia indexing, where it is standard to use multi-modal input for such purposes. This paper describes a novel method for automatic detection...

Domain-specific modelling languages are normally defined through general-purpose meta-modelling languages like the MOF. While this is satisfactory for many Model-Driven Engineering (MDE) projects, several researchers have identified the need for domain-specific metamodelling (DSMM) languages providing customised meta-modelling primitives aimed at the definition of modelling languages in a speci...

This paper reports on and demonstrates META-SHARE/QT21, a prototype implementation of a data sharing and annotation service platform, which was based on the META-SHARE infrastructure. META-SHARE, which has been designed for sharing datasets and tools, is enhanced with a processing layer for annotating textual content with appropriate NLP services that are documented with the appropriate metadat...

This paper presents a meta-learning approach for textual document classification task and an automatic selection of the best available algorithm for creation of classifiers. After brief introductory description of principles of creation and evaluation of the classifiers, the meta-learning approach is presented as a method for automatic selection of the most appropriate classifier algorithm for ...

We describe a high–level approach to the construction of software development environments (SDEs) featuring a new degree of automation. It combines a variety of reuse approaches into one powerful machinery. Based on suitable specification formalisms (context–free grammars as well as graph rewriting systems), generator tools, and a framework implementation, the IPSEN meta environment allows the ...

Recently, XML has become a standard for data representation, manipulation and exchange on the web. The increase in the use of XML in many applicative domains induces a strong need for providing XML query capabilities to many users. In this paper, we propose a solution of XML graphical querying based on the XQuery language. In our approach, we propose to integrate textual, spatial and temporal m...

Meta information in documents is very useful for the management of documents and for information retrieval. Meta information helps in search processes where necessary information is not overtly contained in the text of the document itself, or in documents that contain non-textual information. Assigning topic or keywords to documents helps in identification of relevant documents in search and re...

In many application areas, the key to successful data analysis is the integrated analysis of heterogeneous data. One example is the financial domain, where time-dependent and highly frequent quantitative data (e.g., trading volume and price information) and textual data (e.g., economic and political news reports) need to be considered jointly. Data analysis tools need to support an integrated a...

By considering Sudoku as a language, where a Sudoku puzzle is an instance of the language, we are able to apply meta-model-based technologies for the implementation of Sudoku, including correctness checking of a puzzle and solving strategies. The description of Sudoku includes not only the structure of Sudoku, but also covers constraints, textual representation, graphical representation, and be...