JHU Summer Workshops - Call for team research proposals (Mounya Elhilali )

Subject: JHU Summer Workshops - Call for team research proposals From: Mounya Elhilali <mounya@xxxxxxxx> Date: Mon, 18 Oct 2010 23:27:06 -0400 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY> --_000_C0AB361F4E02DA49B9666FB29890435002352485A6JHEMTEXVS7win_ Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable JHU Summer Workshop CALL FOR TEAM RESEARCH PROPOSALS (revised) Deadline: Tuesday, November 9, 2010. http://www.clsp.jhu.edu/workshops/ws11/CFP 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 11 to August 19, 2011. An interactive peer-review meeting will refine and select proposals to be funded for a six-week residential team exploration. Proposals should aim to advance the state of the art in any of the various fields of Human Language Technology (HLT). This year, proposals in related areas of Machine Intelligence that share techniques with HLT, such as Computer Vision (CV), are also strongly solicited. Proposals are welcome on any topic of interest to HLT, CV and technically related areas. For example, proposals may address novel topics or long-standing problems in one of the following areas. * SPEECH TECHNOLOGY: Proposals are welcomed that address any aspect of information extraction from speech signal (message, speaker identity, language,...). Of particular interest are proposals for techniques whose performance would be minimally degraded by input signal variations, or which require minimal amounts of training data. * NATURAL LANGUAGE PROCESSING: Proposals for knowledge discovery from text are encouraged, as are proposals in traditional fields such as parsing, machine translation, information extraction, sentiment analysis, summarization, and question answering. Proposals may aim to improve the accuracy or enrich the output of such systems, or extend their reach by improving their speed, scalability, and coverage of languages and genres. * VISUAL SCENE INTERPRETATION: New strategies are needed to parse visual scenes or generic (novel) objects, analyzing an image as a set of spatially related components. Such strategies may integrate global top-down knowledge of scene structure (e.g., generative models) with the kind of rich bottom-up, learned image features that have recently become popular for object detection. They will support both learning and efficient search for the best analysis. * UNSUPERVISED AND SEMI-SUPERVISED LEARNING: Novel techniques that do not require extensive quantities of human annotated data to address any of the challenges above could potentially make large strides in machine performance as well as lead to greater robustness to changes in input conditions. Semi-supervised and unsupervised learning techniques with applications to HLT and CV are therefore of considerable interest. Research topics selected for investigation by teams in past workshops may serve as good examples for your proposal (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 no later than November 12, 2010. Authors passing this initial screening will be invited to Baltimore to present their ideas to a peer-review panel on December 3-5, 2010. 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 2011 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 are selected in accordance with their demonstrated performance. Undergraduate participants, selected through a national search, are rising seniors: new to the field and showing outstanding academic promise. If you are interested in participating in the 2011 Summer Workshop we ask that you submit a one-page research proposal for consideration, detailing the problem to be addressed. If your proposal passes the initial screening, we will invite you to join us for the December 3-5 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. We in turn will make a good faith effort to accommodate any personal/logistical needs to make your six-week participation possible. Proposals should be submitted via e-mail to clsp@xxxxxxxx<mailto:clsp@xxxxxxxx= u> by 4PM EST on Tue, November 9, 2010. ---------------------------------------------------------------- Mounya Elhilali, Ph.D. Department of Electrical and Computer engineering Johns Hopkins University --_000_C0AB361F4E02DA49B9666FB29890435002352485A6JHEMTEXVS7win_ Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable <html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr= osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" = xmlns:dt=3D"uuid:C2F41010-65B3-11d1-A29F-00AA00C14882" xmlns:m=3D"http://sc= hemas.microsoft.com/office/2004/12/omml" xmlns=3D"http://www.w3.org/TR/REC-= html40"> <head> <META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; charset=3Dus-ascii"= > <meta name=3DGenerator content=3D"Microsoft Word 12 (filtered medium)"> <style>  </style>  </head> <body lang=3DEN-US link=3Dblue vlink=3Dpurple> <div class=3DWordSection1> <o:p> </o:p> <pre>JHU Summer Workshop<o:p></o:p></pre><pre>CALL FOR TEAM RESEARCH PROPOS= ALS (revised)<o:p></o:p></pre><pre>Deadline: Tuesday, November 9, 2010.<o:p= ></o:p></pre><pre><o:p> </o:p></pre><pre><a href=3D"http://www.clsp.jhu.edu/workshops/ws11/CFP">http://www.clsp.jhu.edu= /workshops/ws11/CFP</a><o:p></o:p></pre><pre><o:p> </o:p></pre><pre>Th= e Center for Language and Speech Processing at Johns Hopkins<o:p></o:p></pr= e><pre>University invites one-page research proposals for a <o:p></o:p></pr= e><pre>Summer Workshop on Language Engineering, to be held <o:p></o:p></pre= ><pre>in Baltimore, MD, USA, July 11 to August 19, 2011.<o:p></o:p></pre><p= re><o:p> </o:p></pre><pre>An interactive peer-review meeting will refi= ne and select proposals <o:p></o:p></pre><pre>to be funded for a six-week r= esidential team exploration. Proposals <o:p></o:p></pre><pre>should aim to = advance the state of the art in any of the various<o:p></o:p></pre><pre>fie= lds of Human Language Technology (HLT).  This year, proposals in<o:p><= /o:p></pre><pre>related areas of Machine Intelligence that share techniques= with<o:p></o:p></pre><pre>HLT, such as Computer Vision (CV), are also stro= ngly solicited.<o:p></o:p></pre><pre><o:p> </o:p></pre><pre>Proposals = are welcome on any topic of interest to HLT, CV and<o:p></o:p></pre><pre>te= chnically related areas.  For example, proposals may address<o:p></o:p= ></pre><pre>novel topics or long-standing problems in one of the following<= o:p></o:p></pre><pre>areas.<o:p></o:p></pre><pre><o:p> </o:p></pre><pr= e>* SPEECH TECHNOLOGY:  Proposals are welcomed that address any<o:p></= o:p></pre><pre>  aspect of information extraction from speech signal (= message,<o:p></o:p></pre><pre>  speaker identity, language,...). Of pa= rticular interest are<o:p></o:p></pre><pre>  proposals for techniques = whose performance would be minimally<o:p></o:p></pre><pre>  degraded b= y input signal variations, or which require minimal<o:p></o:p></pre><pre>&n= bsp; amounts of training data.<o:p></o:p></pre><pre><o:p> </o:p></pre>= <pre>* NATURAL LANGUAGE PROCESSING: Proposals for knowledge discovery<o:p><= /o:p></pre><pre>  from text are encouraged, as are proposals in tradit= ional<o:p></o:p></pre><pre>  fields such as parsing, machine translati= on, information<o:p></o:p></pre><pre>  extraction, sentiment analysis,= summarization, and question<o:p></o:p></pre><pre>  answering.  P= roposals may aim to improve the accuracy or enrich<o:p></o:p></pre><pre>&nb= sp; the output of such systems, or extend their reach by improving<o:p></o:= p></pre><pre>  their speed, scalability, and coverage of languages and= genres.<o:p></o:p></pre><pre><o:p> </o:p></pre><pre>* VISUAL SCENE IN= TERPRETATION: New strategies are needed to<o:p></o:p></pre><pre>  pars= e visual scenes or generic (novel) objects, analyzing an<o:p></o:p></pre><p= re>  image as a set of spatially related components.  Such strate= gies<o:p></o:p></pre><pre>  may integrate global top-down knowledge of= scene structure (e.g.,<o:p></o:p></pre><pre>  generative models) with= the kind of rich bottom-up, learned<o:p></o:p></pre><pre>  image feat= ures that have recently become popular for object<o:p></o:p></pre><pre>&nbs= p; detection.  They will support both learning and efficient search<o:= p></o:p></pre><pre>  for the best analysis.<o:p></o:p></pre><pre><o:p>=  </o:p></pre><pre>* UNSUPERVISED AND SEMI-SUPERVISED LEARNING: Novel t= echniques<o:p></o:p></pre><pre>  that do not require extensive quantit= ies of human annotated data<o:p></o:p></pre><pre>  to address any of t= he challenges above could potentially make<o:p></o:p></pre><pre>  larg= e strides in machine performance as well as lead to greater<o:p></o:p></pre= ><pre>  robustness to changes in input conditions.  Semi-supervis= ed and<o:p></o:p></pre><pre>  unsupervised learning techniques with ap= plications to HLT and CV<o:p></o:p></pre><pre>  are therefore of consi= derable interest.<o:p></o:p></pre><pre><o:p> </o:p></pre><pre>Research= topics selected for investigation by teams in<o:p></o:p></pre><pre>past wo= rkshops may serve as good examples for your proposal<o:p></o:p></pre><pre>(= <a href=3D"http://www.clsp.jhu.edu/workshops">http://www.clsp.jhu.edu/workshop= s</a>).<o:p></o:p></pre><pre><o:p> </o:p></pre><pre>An independent pan= el of experts will screen all received proposals<o:p></o:p></pre><pre>for s= uitability. Results of this screening will be communicated<o:p></o:p></pre>= <pre>no later than November 12, 2010. Authors passing this initial<o:p></o:= p></pre><pre>screening will be invited to Baltimore to present their ideas<= o:p></o:p></pre><pre>to a peer-review panel on December 3-5, 2010.  It= is expected<o:p></o:p></pre><pre>that the proposals will be revised at thi= s meeting to address any<o:p></o:p></pre><pre>outstanding concerns or new i= deas. Two or three research topics and<o:p></o:p></pre><pre>the teams to ta= ckle them will be selected for the 2011 workshop.<o:p></o:p></pre><pre><o:p= > </o:p></pre><pre>We attempt to bring the best researchers to the wor= kshop<o:p></o:p></pre><pre>to collaboratively pursue the selected topics fo= r six weeks.<o:p></o:p></pre><pre>Authors of successful proposals typically= become the team leaders.<o:p></o:p></pre><pre>Each topic brings together a= diverse team of researchers and<o:p></o:p></pre><pre>students.  The s= enior participants come from academia, industry<o:p></o:p></pre><pre>and go= vernment.  Graduate student participants familiar with<o:p></o:p></pre= ><pre>the field are selected in accordance with their demonstrated<o:p></o:= p></pre><pre>performance. Undergraduate participants, selected through a<o:= p></o:p></pre><pre>national search, are rising seniors: new to the field an= d showing<o:p></o:p></pre><pre>outstanding academic promise.<o:p></o:p></pr= e><pre><o:p> </o:p></pre><pre>If you are interested in participating i= n the 2011 Summer<o:p></o:p></pre><pre>Workshop we ask that you submit a on= e-page research proposal for<o:p></o:p></pre><pre>consideration, detailing = the problem to be addressed.  If your<o:p></o:p></pre><pre>proposal pa= sses the initial screening, we will invite you to join<o:p></o:p></pre><pre= >us for the December 3-5 meeting in Baltimore (as our guest) for<o:p></o:p>= </pre><pre>further discussions aimed at consensus.  If a topic in your= area<o:p></o:p></pre><pre>of interest is chosen as one of the two or three= to be pursued<o:p></o:p></pre><pre>next summer, we expect you to be availa= ble for participation<o:p></o:p></pre><pre>in the six-week workshop. We are= not asking for an ironclad<o:p></o:p></pre><pre>commitment at this junctur= e, just a good faith understanding<o:p></o:p></pre><pre>that if a project i= n your area of interest is chosen, you will<o:p></o:p></pre><pre>actively p= ursue it.  We in turn will make a good faith effort to<o:p></o:p></pre= ><pre>accommodate any personal/logistical needs to make your six-week<o:p><= /o:p></pre><pre>participation possible.<o:p></o:p></pre><pre><o:p> </o= :p></pre><pre>Proposals should be submitted via e-mail to <a href=3D"mailto:clsp@xxxxxxxx">clsp@xxxxxxxx</a> by <o:p></o:p></pre><pre><spa= n lang=3DFR>4PM EST on Tue, November 9, 2010.<o:p></o:p></pre> <o:p> </o:p> <o:p> </o:p> ------------------------------------------------------= ----------<o:p></o:p> Mounya Elhilali, Ph.D.<o:p></o:p> Department of Electrical and Computer engineering<o:p>= </o:p> Johns Hopkins University<o:p></o:p> <o:p> </o:p> </div> </body> </html> --_000_C0AB361F4E02DA49B9666FB29890435002352485A6JHEMTEXVS7win_--

This message came from the mail archive
/home/empire6/dpwe/public_html/postings/2010/
maintained by:

DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University