[Elsnet-list] JHU Summer Workshop on Language Engineering - Call for Proposals

Jason Eisner jason at cs.jhu.edu
Thu Sep 28 13:52:40 CEST 2006


JHU Summer Workshops
CALL FOR PROPOSALS
Deadline: ** Wednesday, October 18, 2006 **

The Center for Language and Speech Processing at Johns Hopkins
University invites one-page research proposals for a Summer Workshop
on Language Engineering, to be held in Baltimore, MD, USA, July 9 to
August 17, 2007.

You may already know about these six-week summer workshops, which we
have hosted since 1995. This year, we have identified specific
research topics on which progress is desired.  We are therefore
soliciting research proposals (suitable for a six-week team
exploration) in the following research areas:

* MULTIDOCUMENT, MULTILINGUAL ENTITY DISAMBIGUATION: Content
extraction is an extremely important area of research.  Entity
disambiguation -- determining whether two entity mentions have the 
same referent -- is a very important sub-problem. Disambiguation is
challenging within one document; it is even more challenging and more
important across documents, especially in multilingual and/or
multi-genre collections. The ultimate goal is to have algorithmic
methods for identifying all of the unique entities in a collection of
documents of varied types and in several languages, associating each
entity, including nicknames, name variations, misspellings,
translations, transliterations, and anaphors, with all of its
mentions. Solutions to this or a subset of this problem are of
significant interest.

* AUTOMATIC ADAPTATION OF SPEECH TECHNOLOGY TO NEW DOMAINS: A
recurring problem in creating and refining speech technology is the
time and effort required for data annotation.  Another is the need to
update models as channels, speakers, and vocabularies change over
time.  It would be extremely helpful to have algorithms that could
automatically adapt themselves as their input data evolves.  It would
also be very helpful to study techniques for making systems trained
on large amounts (e.g., thousands of hours) of data from a variety of
domains (different subject matters, styles, speakers, and channels)
perform nearly as well on unfamiliar domains using only tens of hours
of annotated data from those domains. Techniques that use large
amounts of unannotated data from new domains would also be
appropriate.

* SOCIAL NETWORKS AND LANGUAGE: Identifying groups and social roles
of individuals from the frequency and linguistic content of
communications poses questions at the intersection of social network
theory, graph theory and natural language processing. Previous work
on the topology of social networks unveiled surprising
characteristics of human networks (e.g., Milgram's experiments of the
60's) and of the connectivity of websites on the Internet. It would
be helpful to understand how these theories apply to on-line
communities associated with blogs, chat-rooms, instant messaging,
etc. Algorithmic solutions that accurately identify groups in these
communities are particularly desired.

Research topics selected for investigation by teams in previous
workshops may serve as good examples for your proposal. (See 
http://www.clsp.jhu.edu/workshops .)

An independent panel of experts will screen all received proposals
for suitability. Results of this screening will be communicated
within a day of receipt of the proposal, and no later than October
19, 2006. Authors of proposals passing this initial screening will be
invited to Baltimore to present their ideas to a peer-review panel on
November 3-5, 2006. It is expected that the proposals will be revised
at this meeting to address any outstanding concerns or new ideas. Two
or three research topics and the teams to tackle them will be
selected for the 2007 workshop.

We attempt to bring the best researchers to the workshop to
collaboratively pursue the selected topics for six weeks.  Authors of
successful proposals typically become the team leaders.  Each topic
brings together a diverse team of researchers and students.  The
senior participants come from academia, industry and government.
Graduate student participants familiar with the field and are
selected in accordance with their demonstrated performance, usually
by the senior researchers. Undergraduate participants, selected
through a national search, are rising seniors who are new to the
field and have shown outstanding academic promise.

If you are interested and available to participate in the 2007 Summer
Workshop we ask that you submit a one-page research proposal for
consideration, detailing the problem to be addressed and a rough work
agenda for the workshop.  If your proposal passes the initial
screening, we will invite you to join us for the organizational
meeting in Baltimore (as our guest) for further discussions aimed at
consensus.  If a topic in your area of interest is chosen as one of
the two or three to be pursued next summer, we expect you to be
available for participation in the six-week workshop. We are not
asking for an ironclad commitment at this juncture, just a good faith
understanding that if a project in your area of interest is chosen,
you will actively pursue it.

Proposals should be submitted via e-mail to clsp at jhu.edu by 5PM ET on
Wed, October 18, 2006.


More information about the Elsnet-list mailing list