Motivated by eScience applications, we explore automatic generation of example "starter" queries over unstructured collections of tables without relying on a schema, a query log, or prior input from users. Such example queries are demonstrably sufficient to have non-experts self-train and become productive using SQL, helping to increase the uptake of database technology among scientists.</p> <p>Our method is to learn a model for each relational operator based on example queries from public databases, then assemble queries syntactically operator-by-operator. For example, the likelihood that a pair of attributes will be used as a join condition in an example query depends on the cardinality of their intersection, among other features. Our demonstration illustrates that datasets with different statistical properties lead to different sets of example queries with different properties.
%0 Conference Paper
%1 Howe:2011:AEQ:1989323.1989487
%A Howe, Bill
%A Cole, Garret
%A Khoussainova, Nodira
%A Battle, Leilani
%B Proceedings of the 2011 ACM SIGMOD International Conference on Management of data
%C New York, NY, USA
%D 2011
%I ACM
%K escience online query service share sql visualdb
%P 1319--1322
%R 10.1145/1989323.1989487
%T Automatic example queries for ad hoc databases
%U http://doi.acm.org/10.1145/1989323.1989487
%X Motivated by eScience applications, we explore automatic generation of example "starter" queries over unstructured collections of tables without relying on a schema, a query log, or prior input from users. Such example queries are demonstrably sufficient to have non-experts self-train and become productive using SQL, helping to increase the uptake of database technology among scientists.</p> <p>Our method is to learn a model for each relational operator based on example queries from public databases, then assemble queries syntactically operator-by-operator. For example, the likelihood that a pair of attributes will be used as a join condition in an example query depends on the cardinality of their intersection, among other features. Our demonstration illustrates that datasets with different statistical properties lead to different sets of example queries with different properties.
%@ 978-1-4503-0661-4
@inproceedings{Howe:2011:AEQ:1989323.1989487,
abstract = {Motivated by eScience applications, we explore automatic generation of example "starter" queries over unstructured collections of tables without relying on a schema, a query log, or prior input from users. Such example queries are demonstrably sufficient to have non-experts self-train and become productive using SQL, helping to increase the uptake of database technology among scientists.</p> <p>Our method is to learn a model for each relational operator based on example queries from public databases, then assemble queries syntactically operator-by-operator. For example, the likelihood that a pair of attributes will be used as a join condition in an example query depends on the cardinality of their intersection, among other features. Our demonstration illustrates that datasets with different statistical properties lead to different sets of example queries with different properties.},
acmid = {1989487},
added-at = {2012-11-14T16:41:02.000+0100},
address = {New York, NY, USA},
author = {Howe, Bill and Cole, Garret and Khoussainova, Nodira and Battle, Leilani},
biburl = {https://www.bibsonomy.org/bibtex/26935d06ad86b2a58f254661100079633/sac},
booktitle = {Proceedings of the 2011 ACM SIGMOD International Conference on Management of data},
description = {Automatic example queries for ad hoc databases},
doi = {10.1145/1989323.1989487},
interhash = {743194854ff273f74d2fdcd4706b93c0},
intrahash = {6935d06ad86b2a58f254661100079633},
isbn = {978-1-4503-0661-4},
keywords = {escience online query service share sql visualdb},
location = {Athens, Greece},
numpages = {4},
pages = {1319--1322},
publisher = {ACM},
series = {SIGMOD '11},
timestamp = {2012-11-14T16:41:02.000+0100},
title = {Automatic example queries for ad hoc databases},
url = {http://doi.acm.org/10.1145/1989323.1989487},
year = 2011
}