VizierDB
/
paper-HILDA-2016-Spreadsheets
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Related work and abbreviated citations.

master
Oliver Kennedy 2016-04-24 16:40:34 -04:00
parent cfc84dbe93
commit c60aa5ab1d
4 changed files with 331 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

299
HILDA.bib Normal file
View File

@ -0,0 +1,299 @@
%% This BibTeX bibliography file was created using BibDesk.
%% http://bibdesk.sourceforge.net/
%% Created for Oliver Kennedy at 2016-04-24 16:40:02 -0400
%% Saved with string encoding Unicode (UTF-8)
@inproceedings{Zloof:1975:QE:1499949.1500034,
Acmid = {1500034},
Author = {M. M. Zloof},
Booktitle = {AFIPS},
Date-Added = {2016-04-24 20:24:23 +0000},
Date-Modified = {2016-04-24 20:40:01 +0000},
Doi = {10.1145/1499949.1500034},
Location = {Anaheim, California},
Numpages = {8},
Title = {Query by Example},
Url = {http://doi.acm.org/10.1145/1499949.1500034},
Year = {1975},
Bdsk-Url-1 = {http://doi.acm.org/10.1145/1499949.1500034},
Bdsk-Url-2 = {http://dx.doi.org/10.1145/1499949.1500034}}
@inproceedings{Witkowski:2005:QE:1083592.1083733,
Acmid = {1083733},
Author = {A. Witkowski and S. Bellamkonda and T. Bozkaya and A. Naimat and L. Sheng and S. Subramanian and A. Waingold},
Booktitle = {VLDB},
Date-Added = {2016-04-24 20:24:05 +0000},
Date-Modified = {2016-04-24 20:39:36 +0000},
Isbn = {1-59593-154-6},
Location = {Trondheim, Norway},
Numpages = {12},
Title = {{Query by Excel}},
Url = {http://dl.acm.org.gate.lib.buffalo.edu/citation.cfm?id=1083592.1083733},
Year = {2005},
Bdsk-Url-1 = {http://dl.acm.org.gate.lib.buffalo.edu/citation.cfm?id=1083592.1083733}}
@inproceedings{Witkowski:2003:SRO:872757.872767,
Acmid = {872767},
Author = {A. Witkowski and S. Bellamkonda and T. Bozkaya and G. Dorman and N. Folkert and A. Gupta and L. Shen and S. Subramanian},
Booktitle = {SIGMOD},
Date-Added = {2016-04-24 20:24:05 +0000},
Date-Modified = {2016-04-24 20:39:10 +0000},
Doi = {10.1145/872757.872767},
Isbn = {1-58113-634-X},
Location = {San Diego, California},
Numpages = {12},
Title = {Spreadsheets in {RDBMS} for {OLAP}},
Url = {http://doi.acm.org.gate.lib.buffalo.edu/10.1145/872757.872767},
Year = {2003},
Bdsk-Url-1 = {http://doi.acm.org.gate.lib.buffalo.edu/10.1145/872757.872767},
Bdsk-Url-2 = {http://dx.doi.org/10.1145/872757.872767}}
@inproceedings{Tyszkiewicz:2010:SRD:1807167.1807191,
Acmid = {1807191},
Author = {J. Tyszkiewicz},
Booktitle = {SIGMOD},
Date-Added = {2016-04-24 20:23:56 +0000},
Date-Modified = {2016-04-24 20:38:23 +0000},
Doi = {10.1145/1807167.1807191},
Isbn = {978-1-4503-0032-2},
Location = {Indianapolis, Indiana, USA},
Numpages = {12},
Title = {Spreadsheet As a Relational Database Engine},
Url = {http://doi.acm.org.gate.lib.buffalo.edu/10.1145/1807167.1807191},
Year = {2010},
Bdsk-Url-1 = {http://doi.acm.org.gate.lib.buffalo.edu/10.1145/1807167.1807191},
Bdsk-Url-2 = {http://dx.doi.org/10.1145/1807167.1807191}}
@techreport{Sowell:2009aa,
Abstract = {Recent work has shown that we can dramatically improve the performance of computer games and simulations through declarative processing: Character AI can be written in an imperative scripting language which is then compiled to relational algebra and executed by a special games engine with features similar to a main memory database system. In this paper we lay out a challenging research agenda built on these ideas.},
Author = {B. Sowell and A. Demers and J. Gehrke and N. Gupta and H. Li and W. White},
Date-Added = {2016-04-24 20:23:33 +0000},
Date-Modified = {2016-04-24 20:38:08 +0000},
Eprint = {0909.1770},
Institution = {ArXiV},
Title = {From Declarative Languages to Declarative Processing in Computer Games},
Url = {http://arxiv.org/abs/0909.1770},
Year = {2009},
Bdsk-Url-1 = {http://arxiv.org/abs/0909.1770}}
@inproceedings{SV08,
Author = {C. E. Scheidegger and H. Vo and D. Koop and J. Freire and C. T. Silva},
Booktitle = {SIGMOD},
Date-Added = {2016-04-24 20:23:13 +0000},
Date-Modified = {2016-04-24 20:37:35 +0000},
Title = {{Querying and Re-using Workflows with VisTrails}},
Year = {2008}}
@book{saltzer2009principles,
Author = {J. H. Saltzer and M. F. Kaashoek},
Date-Added = {2016-04-24 20:22:47 +0000},
Date-Modified = {2016-04-24 20:36:58 +0000},
Publisher = {Morgan Kaufmann},
Title = {Principles of computer system design: an introduction},
Year = {2009}}
@inproceedings{Olston:2008:PLN:1376616.1376726,
Acmid = {1376726},
Author = {C. Olston and B. Reed and U. Srivastava and R. Kumar and A. Tomkins},
Booktitle = {SIGMOD},
Date-Added = {2016-04-24 20:22:21 +0000},
Date-Modified = {2016-04-24 20:36:32 +0000},
Doi = {10.1145/1376616.1376726},
Isbn = {978-1-60558-102-6},
Keywords = {dataflow language, pig latin},
Location = {Vancouver, Canada},
Numpages = {12},
Title = {{Pig Latin}: {A} Not-so-foreign Language for Data Processing},
Url = {http://doi.acm.org/10.1145/1376616.1376726},
Year = {2008},
Bdsk-Url-1 = {http://doi.acm.org/10.1145/1376616.1376726},
Bdsk-Url-2 = {http://dx.doi.org/10.1145/1376616.1376726}}
@inproceedings{Liu:2009:SAD:1546683.1547431,
Acmid = {1547431},
Author = {B. Liu and H. V. Jagadish},
Booktitle = {ICDE},
Date-Added = {2016-04-24 20:21:55 +0000},
Date-Modified = {2016-04-24 20:35:59 +0000},
Doi = {10.1109/ICDE.2009.34},
Isbn = {978-0-7695-3545-6},
Keywords = {database usability, user interface, spreadsheet},
Numpages = {12},
Title = {A Spreadsheet Algebra for a Direct Data Manipulation Query Interface},
Url = {http://dx.doi.org/10.1109/ICDE.2009.34},
Year = {2009},
Bdsk-Url-1 = {http://dx.doi.org/10.1109/ICDE.2009.34}}
@inproceedings{Kandel:2011:WIV:1978942.1979444,
Acmid = {1979444},
Author = {S. Kandel and A. Paepcke and J. Hellerstein and J. Heer},
Booktitle = {SIGCHI},
Date-Added = {2016-04-24 20:21:30 +0000},
Date-Modified = {2016-04-24 20:35:41 +0000},
Doi = {10.1145/1978942.1979444},
Isbn = {978-1-4503-0228-9},
Keywords = {data analysis, data cleaning, transformation, visualization, wrangler},
Location = {Vancouver, BC, Canada},
Numpages = {10},
Title = {{Wrangler}: Interactive Visual Specification of Data Transformation Scripts},
Url = {http://doi.acm.org/10.1145/1978942.1979444},
Year = {2011},
Bdsk-Url-1 = {http://doi.acm.org/10.1145/1978942.1979444},
Bdsk-Url-2 = {http://dx.doi.org/10.1145/1978942.1979444}}
@article{JC07,
Author = {H. V. Jagadish and A. Chapman and A. Elkiss and M. Jayapandian and Y. Li and A. Nandi and C. Yu},
Date-Added = {2016-04-24 20:21:01 +0000},
Date-Modified = {2016-04-24 20:35:18 +0000},
Journal = {SIGMOD},
Title = {{Making database systems usable}},
Year = {2007}}
@inproceedings{HL08,
Author = {B. Howe and P. Lawson and R. Bellinger and E. W. Anderson and E. Santos and J. Freire and C. E. Scheidegger and A. Baptista and C. T. Silva},
Booktitle = {eScience},
Date-Added = {2016-04-24 20:20:31 +0000},
Date-Modified = {2016-04-24 20:34:08 +0000},
Title = {{End-to-End eScience: Integrating Workflow, Query, Visualization, and Provenance at an Ocean Observatory}},
Year = {2008}}
@incollection{FS06,
Author = {J. Freire and C. T. Silva and S. P. Callahan and E. Santos and C. E. Scheidegger and H. T. Vo},
Booktitle = {PAD},
Date-Added = {2016-04-24 20:19:52 +0000},
Date-Modified = {2016-04-24 20:33:18 +0000},
Pages = {10--18},
Publisher = {Springer},
Title = {Managing rapidly-evolving scientific workflows},
Year = {2006}}
@inbook{Erwig2002,
Address = {Berlin, Heidelberg},
Author = {M. Erwig and M. Burnett},
Chapter = {Adding Apples and Oranges},
Date-Added = {2016-04-24 20:19:28 +0000},
Date-Modified = {2016-04-24 20:34:29 +0000},
Doi = {10.1007/3-540-45587-6_12},
Isbn = {978-3-540-45587-5},
Pages = {173--191},
Publisher = {Springer Berlin Heidelberg},
Title = {Practical Aspects of Declarative Languages},
Url = {http://dx.doi.org/10.1007/3-540-45587-6_12},
Year = {2002},
Bdsk-Url-1 = {http://dx.doi.org/10.1007/3-540-45587-6_12}}
@article{DC07,
Author = {S. B. Davidson and S. Cohen-Boulakia and A. Eyal and B. Lud\"{a}scher and T. McPhillips and S. Bowers and J. Freire},
Date-Added = {2016-04-24 20:19:10 +0000},
Date-Modified = {2016-04-24 20:31:20 +0000},
Journal = {IEEE DEB},
Number = {4},
Pages = {44--50},
Title = {{Provenance in Scientific Workflow Systems}},
Volume = {32},
Year = {2007}}
@incollection{CF12a,
Author = {F. Chirigati and J. Freire},
Booktitle = {PADP},
Date-Added = {2016-04-24 20:18:59 +0000},
Date-Modified = {2016-04-24 20:30:07 +0000},
Pages = {11--23},
Publisher = {Springer},
Title = {Towards integrating workflow and database provenance},
Year = {2012}}
@article{Chan1996119,
Abstract = {Spreadsheets have long been recognized as important tools for end-user computing. This research explores their use within business organizations. A survey was carried out to investigate the relationships among tasks, spreadsheet proficiency, usage, and satisfaction. The results suggested that the spreadsheet proficiency can have a greater impact on the tasks than the task can have on the spreadsheet proficiency. It was also found that spreadsheet users often do not use many of the commonly available spreadsheet features, and they do not appear inclined to use other software packages for their tasks, even if these packages might be more suitable. The proficiency of the spreadsheet users was not found to be related to the importance of the decisions being taken as a result of the spreadsheet analyses. },
Author = {Y. E. Chan and V. C. Storey},
Date-Added = {2016-04-24 20:18:23 +0000},
Date-Modified = {2016-04-24 20:29:43 +0000},
Journal = {JIDM},
Number = {3},
Pages = {119 - 134},
Title = {The use of spreadsheets in organizations: Determinants and consequences},
Volume = {31},
Year = {1996},
Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/pii/S0378720696000080},
Bdsk-Url-2 = {http://dx.doi.org/10.1016/S0378-7206(96)00008-0}}
@article{Bendre:2015:DUD:2824032.2824121,
Acmid = {2824121},
Author = {Bendre, Mangesh and Sun, Bofan and Zhang, Ding and Zhou, Xinyan and Chang, Kevin Chen-Chuan and Parameswaran, Aditya},
Date-Added = {2016-04-24 20:18:06 +0000},
Date-Modified = {2016-04-24 20:28:25 +0000},
Doi = {10.14778/2824032.2824121},
Issn = {2150-8097},
Issue_Date = {August 2015},
Journal = {pVLDB},
Number = {12},
Numpages = {4},
Pages = {2000--2003},
Publisher = {VLDB Endowment},
Title = {{DataSpread}: {U}nifying Databases and Spreadsheets},
Url = {http://dx.doi.org/10.14778/2824032.2824121},
Volume = {8},
Year = {2015},
Bdsk-Url-1 = {http://dx.doi.org/10.14778/2824032.2824121}}
@inproceedings{Bakke:2011:SUI:1978942.1979313,
Acmid = {1979313},
Author = {E. Bakke and D. Karger and R. Miller},
Booktitle = {SIGCHI},
Date-Added = {2016-04-24 20:17:48 +0000},
Date-Modified = {2016-04-24 20:28:05 +0000},
Doi = {10.1145/1978942.1979313},
Isbn = {978-1-4503-0228-9},
Keywords = {databases, foreign key relationships, hierarchical views, one-to-many relationships, spreadsheets},
Location = {Vancouver, BC, Canada},
Numpages = {10},
Title = {A Spreadsheet-based User Interface for Managing Plural Relationships in Structured Data},
Url = {http://doi.acm.org/10.1145/1978942.1979313},
Year = {2011},
Bdsk-Url-1 = {http://doi.acm.org/10.1145/1978942.1979313},
Bdsk-Url-2 = {http://dx.doi.org/10.1145/1978942.1979313}}
@article{bakke2011schema,
Author = {E. Bakke and E. Benson},
Date-Added = {2016-04-24 20:17:48 +0000},
Date-Modified = {2016-04-24 20:27:47 +0000},
Journal = {CIDR},
Publisher = {Citeseer},
Title = {{The Schema-Independent Database UI}: {A} Proposed Holy Grail and Some Suggestions},
Year = {2011}}
@techreport{AG16,
Author = {B. Arab and D. Gawlick and V. Krishnaswamy and V. Radhakrishnan and B. Glavic},
Date-Added = {2016-04-24 20:17:27 +0000},
Date-Modified = {2016-04-24 20:27:03 +0000},
Institution = {Illinois Institute of Technology},
Number = {IIT/CS-DB-2016-01},
Title = {Formal Foundations of Reenactment and Transaction Provenance},
Year = {2016}}
@techreport{AG14a,
Author = {B. Arab and D. Gawlick and V. Krishnaswamy and V. Radhakrishnan and B. Glavic},
Date-Added = {2016-04-24 20:17:05 +0000},
Date-Modified = {2016-04-24 20:26:28 +0000},
Institution = {Illinois Institute of Technology},
Keywords = {temporal-provenance; provenance; transactions; reenactment; GProM},
Number = {IIT/CS-DB-2014-02},
Title = {Reenacting Transactions to Compute their Provenance},
Venueshort = {Techreport},
Year = {2014}}
@article{AD11c,
Author = {Amsterdamer, Y. and Davidson, S. B. and Deutch, D. and Milo, T. and Stoyanovich, J. and Tannen, V.},
Date-Added = {2016-04-24 20:16:20 +0000},
Date-Modified = {2016-04-24 20:30:21 +0000},
Journal = {pVLDB},
Number = {4},
Pages = {346--357},
Title = {Putting {Lipstick on Pig}: Enabling Database-style Workflow Provenance},
Volume = {5},
Year = {2011}}

4
main.tex
View File

@ -53,6 +53,8 @@ Juliana Freire$^n$, Boris Glavic$^i$, Oliver Kennedy$^b$, Heiko Mueller$^n$\\
\label{sec:related}
\input{sections/related}
{\small
\bibliographystyle{plain}
\bibliography{freire,okennedy,urban,vistrails,vizier}
\bibliography{HILDA}
}
\end{document}

17
okennedy.bib
View File

@ -207,3 +207,20 @@
acmid = {1083733},
publisher = {VLDB Endowment},
}
@inproceedings{Witkowski:2003:SRO:872757.872767,
author = {Witkowski, Andrew and Bellamkonda, Srikanth and Bozkaya, Tolga and Dorman, Gregory and Folkert, Nathan and Gupta, Abhinav and Shen, Lei and Subramanian, Sankar},
title = {Spreadsheets in RDBMS for OLAP},
booktitle = {Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data},
series = {SIGMOD '03},
year = {2003},
isbn = {1-58113-634-X},
location = {San Diego, California},
pages = {52--63},
numpages = {12},
url = {http://doi.acm.org.gate.lib.buffalo.edu/10.1145/872757.872767},
doi = {10.1145/872757.872767},
acmid = {872767},
publisher = {ACM},
address = {New York, NY, USA},
}

28
sections/related.tex
View File

@ -1,24 +1,20 @@
%!TEX root = ../main.tex
Spreadsheet style interfaces for relational data have been of interest to researchers and practitioners alike for some time now.
In \cite{Tyszkiewicz:2010:SRD:1807167.1807191}, Tyszkiewicz demonstrated an embedding of SQL into spreadsheet formula semantics.
Furthermore, Excel already includes minimal database integration capabilities, and there exists a spectrum of existing attempts at hybrid environments~\cite{Bakke:2011:SUI:1978942.1979313, bakke2011schema, Kandel:2011:WIV:1978942.1979444, Bendre:2015:DUD:2824032.2824121,Liu:2009:SAD:1546683.1547431}.
Trifacta/Wrangler~\cite{Kandel:2011:WIV:1978942.1979444} is one of the more spiritually similar. As in \sysname, users generate curation workflows by directly editing data. However, unlike \sysname, there is no support for singleton operations in the workflow language; User edits must be generalized immediately through a helpful suggestion interface.
Query-by-Excel~\cite{Witkowski:2003:SRO:872757.872767,Witkowski:2005:QE:1083592.1083733} (QBX) provides support for cube-style queries operations in a spreadsheet-like environment. Although the goal is different, the mechanism is quite similar: QBX allows singleton outputs in the cube query, encoding them as \texttt{UPDATE} operations on the query output. However, QBX treats only query outputs as mutable, while source data is fixed; \langname is free of this limitation.
SheetMusiq~\cite{Liu:2009:SAD:1546683.1547431} uses a semantics for relational queries over spreadsheets. Though superficially similar to \langname, it assumes static data, and does not attempt to preserve formula semantics through queries.
Related Worksheets~\cite{Bakke:2011:SUI:1978942.1979313, bakke2011schema} provides a spreadsheet UI for structured relational data, focusing in particular on enabling strongly typed data and foreign key references. However, although editing cells is permitted, the work does not address cell formulas.
DataSpread~\cite{Bendre:2015:DUD:2824032.2824121} extends spreadsheets with relational database functionality: structured query support and a scalable relational data engine for a backend. By comparison, \langname instead starts with a structured relational data model and extends it with the illusion of freeform editing.
The idea of generalizing singleton operations is based on Query by Example~\cite{Zloof:1975:QE:1499949.1500034}, as well as Query by Explanation \url{http://arxiv.org/abs/1602.03819}. As individual operations are grouped together, the system can, in effect, learn to describe what the user is attempting to accomplish. We plan to draw heavily on work in this area to develop \sysname's generalization engine.
Two other areas we have drawn on heavily for the design of \sysname are scientific workflows~\cite{FS06,HL08,SV08,CF12a,AD11c,DC07}, which form the basis for the notebook-style interface; as well as
reenactment~\cite{AG14a,AG16}, which forms the basis for \langname scripts.
\begin{itemize}
\item Query by Example
\item Query by Explanation \url{http://arxiv.org/abs/1602.03819}
\item Trifacta/Wrangler/Potter's Wheel
\item Similar, but forces upfront generalization.
\item Provenance for edits
\item View maintenance?
\item Workflow systems (VisTrails)
\item Reenactment
\end{itemize}
The simplicity of spreadsheets, combined with spreadsheet users who ``do not appear inclined to use other software packages for their tasks, even if these packages might be more suitable"~\cite{Chan1996119},
has encouraged many database-driven efforts to resolve the impedance mismatch between positional and set-at-a-time query semantics~\cite{LJ09,JC07}, make spreadsheets more structured~\cite{Bakke:2011:SUI:1978942.1979313,bakke2011schema} or make databases more spreadsheet-like~\cite{DBLP:journals/ijcse/JagadishQN15}.
%%% Local Variables:
%%% mode: latex
%%% TeX-master: "../main"