Pruning policies for two-tiered inverted index with correctness guarantee Export

@inproceedings{citeulike:2148554, abstract = {The Web search engines maintain large-scale inverted indexes which are queried thousands of times per second by users eager for information. In order to cope with the vast amounts of query loads, search engines prune their index to keep documents that are likely to be returned as top results, and use this pruned index to compute the first batches of results. While this approach can improve performance by reducing the size of the index, if we compute the top results only from the pruned index we may notice a significant degradation in the result quality: if a document should be in the top results but was not included in the pruned index, it will be placed behind the results computed from the pruned index. Given the fierce competition in the online search market, this phenomenon is clearly undesirable.}, address = {New York, NY, USA}, author = {Ntoulas, Alexandros and Cho, Junghoo}, booktitle = {SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {2148554}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1277741.1277776}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1277741.1277776}, doi = {10.1145/1277741.1277776}, isbn = {978-1-59593-597-7}, keywords = {websearchsystems}, location = {Amsterdam, The Netherlands}, pages = {191--198}, posted-at = {2007-12-19 21:48:53}, priority = {0}, publisher = {ACM}, title = {Pruning policies for two-tiered inverted index with correctness guarantee}, url = {http://dx.doi.org/10.1145/1277741.1277776}, year = {2007} }

TY - CONF ID - citeulike:2148554 L3 - citeulike-article-id:2148554 N2 - The Web search engines maintain large-scale inverted indexes which are queried thousands of times per second by users eager for information. In order to cope with the vast amounts of query loads, search engines prune their index to keep documents that are likely to be returned as top results, and use this pruned index to compute the first batches of results. While this approach can improve performance by reducing the size of the index, if we compute the top results only from the pruned index we may notice a significant degradation in the result quality: if a document should be in the top results but was not included in the pruned index, it will be placed behind the results computed from the pruned index. Given the fierce competition in the online search market, this phenomenon is clearly undesirable. CY - Amsterdam, The Netherlands SN - 978-1-59593-597-7 AD - New York, NY, USA EP - 198 TI - Pruning policies for two-tiered inverted index with correctness guarantee PB - ACM T2 - SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval SP - 191 KW - websearchsystems AU - Ntoulas, Alexandros AU - Cho, Junghoo PY - 2007/// UR - http://dx.doi.org/10.1145/1277741.1277776 ER -