|
Letters |
SIGIR
Forum 35(2) |
We would like to make
our resignations public, to explain the rationale for our action, and to
indicate some of the implications that we see for members of the machine
learning community worldwide.
The machine learning
community has come of age during a period of enormous change in the way that
research publications are circulated. Fifteen years ago research papers did not
circulate easily, and as with other research communities we were fortunate that
a viable commercial publishing model was in place so that the fledgling MLJ
could begin to circulate. The needs of the community, principally those of
seeing our published papers circulate as widely and rapidly as possible, and
the business model of commercial publishers were in harmony.
Times have changed. Articles
now circulate easily via the Internet, but unfortunately MLJ publications are
under restricted access. Universities and research centres can pay a yearly fee
of $1050 US to obtain unrestricted access to MLJ articles (and individuals can
pay $120 US). While these fees provide access for institutions and individuals
who can afford them, we feel that they also have the effect of limiting contact
between the current machine learning community and the potentially much larger
community of researchers worldwide whose participation in our field should be
the fruit of the modern Internet.
None of the revenue stream
from the journal makes its way back to authors, and in this context authors
should expect a particularly favorable return on their intellectual
contribution---they should expect a service that maximizes the distribution of
their work. We see little benefit accruing to our community from a mechanism
that ensures revenue for a third party by restricting the communication channel
between authors and readers.
In the spring of 2000, a new journal, the Journal of Machine
Learning Research (JMLR), was created, based on a new vision of the journal
publication process in which the editorial board and authors retain significant
control over the journal's content and distribution. Articles published in JMLR
are available freely, without limits and without conditions, at the journal's
website, http://www.jmlr.org/.
The content and format of the website are entirely controlled by the editorial
board, which also serves its traditional function of ensuring rigorous peer
review of journal articles. Finally, the journal is also published in a
hardcopy version by MIT Press.
Authors retain the copyright
for the articles that they publish in JMLR. The following paragraph is taken
from the agreement that every author signs with JMLR (see http://www.jmlr.org/forms/agreement.pdf):
You [the author] retain
copyright to your article, subject only to the specific rights given to MIT
Press and to the Sponsor [the editorial board] in the following paragraphs. By
retaining your copyright, you are reserving for yourself among other things
unlimited rights of electronic distribution, and the right to license your work
to other publishers, once the article has been published in JMLR by MIT Press
and the Sponsor [the editorial board]. After first publication, your only
obligation is to ensure that appropriate first publication credit is given to
JMLR and MIT Press.
We think that many will agree that this is an agreement that is
reflective of the modern Internet, and is appealing in its recognition of the
rights of authors to distribute their work as widely as possible. In particular,
authors can leave copies of their JMLR articles on their own homepage.
Over the years the editorial
board of MLJ has expanded to encompass all of the various perspectives on the
machine-learning field, and the editorial board's efforts in this regard have contributed
greatly to the sense of intellectual unity and community that many of us feel.
We believe, however, that there is much more to achieve, and that our further
growth and further impact will be enormously enhanced if via our flagship
journal we are able to communicate more freely, easily, and universally.
Our action is not
unprecedented. As documented at the Scholarly Publishing and Academic Resources
Coalition (SPARC) website, http://www.arl.org/sparc, there are many areas in
science where researchers are moving to low-cost publication alternatives. One
salient example is the case of the journal "Logic Programming". In
1999, the editors and editorial advisors of this journal resigned to join
"Theory and Practice of Logic Programming", a Cambridge University
Press journal that encourages electronic dissemination of papers.
In summary, our resignation
from the editorial board of MLJ reflects our belief that journals should
principally serve the needs of the intellectual community, in particular by providing
the immediate and universal access to journal articles that modern technology
supports, and doing so at a cost that excludes no one. We are excited about
JMLR, which provides this access and does so unconditionally. We feel that JMLR
provides an ideal vehicle to support the near-term and long-term evolution of
the field of machine learning and to serve as the flagship journal for the
field. We invite all of the members of the community to submit their articles
to the journal and to contribute actively to its growth.
Sincerely yours,
Chris Atkeson
Peter Bartlett
Andrew Barto
Jonathan Baxter
Yoshua Bengio
Kristin Bennett
Chris Bishop
Justin Boyan
Carla Brodley
Claire Cardie
William Cohen
Peter Dayan
Tom Dietterich
Jerome Friedman
Nir Friedman
Zoubin Ghahramani
David Heckerman
Geoffrey Hinton
Haym Hirsh
Tommi Jaakkola
Michael Jordan
Leslie Kaelbling
Daphne Koller
John Lafferty
Sridhar Mahadevan
Marina Meila
Andrew McCallum
Tom Mitchell
Stuart Russell
Lawrence Saul
Bernhard Schoelkopf
John Shawe-Taylor
Yoram Singer
Satinder Singh
Padhraic Smyth
Richard Sutton
Sebastian Thrun
Manfred Warmuth
Chris Williams
Robert Williamson
Dear colleagues,
In response to the widely
circulated letter of resignation of some members of the Machine Learning
journal (MLJ), I would like to make two points:
The accessibility of MLJ
papers has been dramatically improved in the past 12 months. The main changes
are these:
·
the copyright
agreement gives the author the right to distribute individual copies of an MLJ
paper to students and colleagues, physically and electronically, including
making the paper available from the author's personal web site.
·
the individual
MLJ subscription price has been dramatically reduced. It is excellent value for
money: for $120 Kluwer prints, binds, and mails to your door around 1350 pages.
As a consequence of the
first two points, MLJ articles are universally accessible -- from Kluwer's home
page in the first six months or so, and at any time from the author's home
page.
The primary purpose of paid subscriptions, in this new
distribution model, is to enable an individual or institution to obtain a bound
archival copy of the journal printed on high-quality paper -- exactly the same
role served by the printed version of JMLR sold by MIT Press.
Turning to the second point,
all members of both editorial boards have the interests of the machine learning
community at heart. Our job is to serve you.
The current members of the
MLJ board, and the new members we are in the process of adding, believe it is
in the best interests of the research community to keep MLJ alive and strong at
this time. This is not to say we hope JMLR will fail. There is ample excellent
research to support two high-quality journals, so it is not necessary for one
of the journals to be destroyed in order for the other to succeed.
If you agree that MLJ is
useful to the community and has a role to play in the future, I would like to
hear from you - feedback from the community is the very best way for me to know
how to steer MLJ's course so it best serves the community.
Robert Holte holte@cs.ualberta.ca
Executive EditorMachine
Learning
To the Information Retrieval
Community:
A letter was recently
distributed by Dr. Michael Jordan of UC Berkeley and 39 other prominent researchers
who resigned from the Editorial Board of the Kluwer journal, Machine
Learning. The letter, which argues for
less restrictive access to the archival research literature, can be found in a
recent issue of SIG-IRList
(http://www.acm.org/sigir/sigirlist/) and also at
http://www.cs.orst.edu/~dambrosi/uai-archive/0822.html.
This event is of interest to
the information retrieval community, given that an attempt has been underway
for several years to establish another Kluwer journal, Information Retrieval,
as the core journal in IR. Indeed, I
participated in that attempt in its early years, recruiting a number of the
members of the Editorial Board. It is
important to appreciate the importance to our field of having a journal focused
purely on IR, and it is important to acknowledge the contribution of Paul
Kantor, Steve Robertson, the Editorial Board, and the authors of papers in establishing
this journal.
Over the years,
however, my sentiments have come to largely reflect those of those who recently
left Machine Learning. In July 2001, I
resigned from the Editorial Board of Information Retrieval, and of two other journals
without open archives. The World Wide
Web allows broader distribution of research results than at any previous time
in history, but only if changes are made in how academic publishing works.
It is important to
acknowledge that many things are unclear about how academic publishing will
evolve. How to reconcile open archives
with the financial needs of professional organizations such as ACM is a
particularly difficult question. The role
of conference proceedings, with their quasi-archival status, is also unclear.
These issues are being discussed in a variety of forums, including at:
http://www.nature.com/nature/debates/e-access/
Would an open archive, noncommercial, journal like
JMLR (http://www.jmlr.org/) or
JAIR (http://www.jair.org/) be
viable in information retrieval? I
believe it would, but to forestall the obvious question, I have no plans to
found such a journal myself, or to participate more in this debate than the
hour spent writing this letter. My new
career as a self-supporting consultant doesn't give me that luxury.
What I can do is what each
of us does: choose where to put the time I can afford to volunteer. I now serve only on the Editorial Board of
JAIR, and I accept reviewing requests only from journals with open
archives. If an IR journal with open
archives were to be founded, I would do my best to support it. Further, I will publish journal articles on
which I am the sole author only in journals with open archives.
Regards,
David D. Lewis
openarchemail@daviddlewis.com
Independent Consultant