Both focused retrieval and result aggregation provide the user with answers to their information needs, rather than just pointers to whole documents. Focused retrieval identifies not only relevant documents but also which parts of those documents are relevant, thus reducing the time it takes the user to navigate in a document. Result aggregation is used when the best way to fulfil the user’s need is to draw from many different information sources (different collections, documents, or parts of the same document), and to aggregate these into a single result, thus reducing the time it takes the user to fulfil their information need. This special issue includes seven papers showing the breadth and depth of the current state of research in these two branches of information retrieval. They include descriptions of live result aggregation systems, and experimental focussed retrieval systems including sentence retrieval, question answering, and entity ranking; as well as metrics for passage retrieval. To introduce this special issue, we provide an overview of the work presented in these papers.
[1]
Jaana Kekäläinen,et al.
Expected reading effort in focused retrieval evaluation
,
2010,
Information Retrieval.
[2]
David E. Losada,et al.
Statistical query expansion for sentence retrieval and its effects on weak and strong queries
,
2010,
Information Retrieval.
[3]
Paul Thomas,et al.
Focused and aggregated search: a perspective from natural language generation
,
2010,
Information Retrieval.
[4]
James A. Thom,et al.
Entity ranking in Wikipedia: utilising categories, links and topic difficulty prediction
,
2009,
Information Retrieval.
[5]
Ralf Krestel,et al.
Why finding entities in Wikipedia is difficult, sometimes
,
2010,
Information Retrieval.
[6]
Maarten Marx,et al.
Focused retrieval and result aggregation with political data
,
2010,
Information Retrieval.
[7]
Xavier Tannier,et al.
FIDJI: using syntax for validating answers in multiple documents
,
2010,
Information Retrieval.