@inproceedings{chakrabarti2008an,
author = {Chakrabarti, Kaushik and Chaudhuri, Surajit and Ganti, Venkatesh and Xin, Dong},
title = {An Efficient Filter for Approximate Membership Checking},
booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD 2008)},
year = {2008},
month = {June},
abstract = {We consider the problem of identifying sub-strings of input text strings that approximately match with some member of a potentially large dictionary. This problem arises in several important applications such as extracting named entities from text documents and identifying biological concepts from biomedical literature. In this paper, we develop a fiter-verification framework, and propose a novel in-memory filter structure. That is, we first quickly filter out sub-strings that cannot match with any dictionary member, and then verify the remaining sub-strings against the dictionary. Our method does not produce false negatives. We demonstrate the efficiency and effectiveness of our filter over real datasets, and show that it significantly outperforms the previous best-known methods in terms of both filtering power and computation time.},
publisher = {ACM - Association for Computing Machinery},
url = {http://approjects.co.za/?big=en-us/research/publication/efficient-filter-approximate-membership-checking/},
edition = {Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD 2008)},
}