Comparative evaluation of XML information retrieval systems

Meer over het boek

This book provides a comprehensive overview of various methodologies and evaluations from INEX 2006, focusing on XML retrieval and related tasks. It covers the Wikipedia XML Corpus and evaluation measures, including sensitivity analysis for choosing ideal recall bases. The ad hoc track is discussed alongside methods for preferential unification of plural retrieved elements. Contributions from organizations like CSIRO and IBM highlight dynamic element retrieval and indexing techniques. The text explores efficient XML retrieval using summaries and evaluates structured information retrieval, multimedia retrieval, and probabilistic approaches. Interactive and heterogeneous collection tracks are examined, along with the taxonomy of XML retrieval use cases. The document track includes insights into XML mining and classification based on structural and content similarities. Techniques such as graph neural networks, contextual self-organizing maps, and conditional random fields for document transformation are also presented. Overall, the book encapsulates the advancements and methodologies in XML information retrieval, providing valuable insights for researchers and practitioners in the field.