A time machine for text search Export

@inproceedings{citeulike:4204040, abstract = {Text search over temporally versioned document collections such as web archives has received little attention as a research problem. As a consequence, there is no scalable and principled solution to search such a collection as of a specified time. In this work, we address this shortcoming and propose an efficient solution for time-travel text search by extending the inverted file index to make it ready for temporal search. We introduce approximate temporal coalescing as a tunable method to reduce the index size without significantly affecting the quality of results. In order to further improve the performance of time-travel queries, we introduce two principled techniques to trade off index size for its performance. These techniques can be formulated as optimization problems that can be solved to near-optimality. Finally, our approach is evaluated in a comprehensive series of experiments on two large-scale real-world datasets. Results unequivocally show that our methods make it possible to build an efficient "time machine" scalable to large versioned text collections.}, address = {New York, NY, USA}, author = {Berberich, Klaus and Bedathur, Srikanta and Neumann, Thomas and Weikum, Gerhard}, booktitle = {SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {4204040}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1277831}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1277741.1277831}, doi = {10.1145/1277741.1277831}, isbn = {978-1-59593-597-7}, keywords = {indexing}, location = {Amsterdam, The Netherlands}, pages = {519--526}, posted-at = {2009-10-19 15:38:40}, priority = {0}, publisher = {ACM}, title = {A time machine for text search}, url = {http://dx.doi.org/10.1145/1277741.1277831}, year = {2007} }

TY - CONF ID - citeulike:4204040 L3 - citeulike-article-id:4204040 N2 - Text search over temporally versioned document collections such as web archives has received little attention as a research problem. As a consequence, there is no scalable and principled solution to search such a collection as of a specified time. In this work, we address this shortcoming and propose an efficient solution for time-travel text search by extending the inverted file index to make it ready for temporal search. We introduce approximate temporal coalescing as a tunable method to reduce the index size without significantly affecting the quality of results. In order to further improve the performance of time-travel queries, we introduce two principled techniques to trade off index size for its performance. These techniques can be formulated as optimization problems that can be solved to near-optimality. Finally, our approach is evaluated in a comprehensive series of experiments on two large-scale real-world datasets. Results unequivocally show that our methods make it possible to build an efficient "time machine" scalable to large versioned text collections. CY - Amsterdam, The Netherlands SN - 978-1-59593-597-7 AD - New York, NY, USA EP - 526 TI - A time machine for text search PB - ACM T2 - SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval SP - 519 KW - indexing AU - Berberich, Klaus AU - Bedathur, Srikanta AU - Neumann, Thomas AU - Weikum, Gerhard PY - 2007/// UR - http://dx.doi.org/10.1145/1277741.1277831 ER -