@inproceedings{mccallum00efficient,
        title = {Efficient clustering of high-dimensional data sets with application to reference matching},
        address = {New York, NY, USA},
        author = {Andrew McCallum and Kamal Nigam and Lyle H. Ungar},
        booktitle = {KDD '00: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining},
        pages = {169--178},
        publisher = {ACM Press},
        year = 2000,
        location = {Boston, Massachusetts, United States},
	isbn = {1-58113-233-6},
	doi = {http://doi.acm.org/10.1145/347090.347123},
	description = {Efficient clustering of high-dimensional data sets with application to reference matching},
	biburl = {http://www.bibsonomy.org/bibtex/2346d1db87c3bda5fcf4ec5f92a75e16a/sb3000},
	keywords = {dataset efficiency clustering}
}

@inproceedings{burrows06googlebigtable,
        title = {Bigtable: A Distributed Storage System for Structured Data},
        author = {Fay Chang and Jeffrey Dean and Sanjay Ghemawat and Wilson C. Hsieh and Deborah A. Wallach and Mike Burrows and Tushar Chandra and Andrew Fikes and Robert E. Gruber},
        booktitle = {OSDI'06: Seventh Symposium on Operating System Design and Implementation, Seattle, WA, November, 2006},
        pages = {205--218},
        year = 2006,
        url = {http://labs.google.com/papers/bigtable-osdi06.pdf},
        biburl = {http://www.bibsonomy.org/bibtex/2913bfd5965ad54bb09847d66765bcc04/sb3000},
	keywords = {scalability google fault-tolerance performance distributed efficiency database algorithm}
}