XIRQL: An XML query language based on information retrieval concepts
ACM Transactions on Information Systems (TOIS)
The overlap problem in content-oriented XML retrieval evaluation
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Length normalization in XML retrieval
Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Choosing document structure weights
Information Processing and Management: an International Journal
Structured queries in XML retrieval
Proceedings of the 14th ACM international conference on Information and knowledge management
Generalized contextualization method for XML information retrieval
Proceedings of the 14th ACM international conference on Information and knowledge management
XML retrieval: what about using contextual relevance?
Proceedings of the 2006 ACM symposium on Applied computing
XFIRM at INEX 2005: ad-hoc and relevance feedback tracks
INEX'05 Proceedings of the 4th international conference on Initiative for the Evaluation of XML Retrieval
ECIR'05 Proceedings of the 27th European conference on Advances in Information Retrieval Research
Component ranking and automatic query refinement for XML retrieval
INEX'04 Proceedings of the Third international conference on Initiative for the Evaluation of XML Retrieval
TRIX 2004: struggling with the overlap
INEX'04 Proceedings of the Third international conference on Initiative for the Evaluation of XML Retrieval
The utrecht blend: basic ingredients for an XML retrieval system
INEX'04 Proceedings of the Third international conference on Initiative for the Evaluation of XML Retrieval
Using a relevance propagation method for adhoc and heterogeneous tracks at INEX 2004
INEX'04 Proceedings of the Third international conference on Initiative for the Evaluation of XML Retrieval
Why using structural hints in XML retrieval?
FQAS'06 Proceedings of the 7th international conference on Flexible Query Answering Systems
| Hi-index | 0.00 |
Focussed XML component retrieval is one of the most important challenges in the XML IR field. The aim of the focussed retrieval strategy is to find the most exhaustive and specific element in a path, i.e. to retrieve elements that focus on the user need, without nested elements. In this paper, we introduce a relevance propagation method dealing with focussed XML component retrieval. Many experiments are carried out with the INEX 2005 test suite to define what are the main characteristics of relevant elements in focussed retrieval and to compare such characteristics with those of relevant elements in thorough retrieval (where the aim is to find all relevant elements in the collection). Our main findings are the following. First, a term weighting scheme taking into account the importance of terms in elements and both in collection of elements and collection of documents is useful. Moreover, the introduction of component length as a threshold on results or used in a weighted propagation function improves significantly the results. Third, contextual relevance seems not to be useful, which contradicts results obtained by state-of-the-art methods for non-focussed retrieval. At last, the use of structural hints increases up to 50% performances we obtained when using queries composed only of simple keyword terms.