Best content in Library in Transition

ALA TechSource | Dear Library of Congress... - 0 views

www.techsource.ala.org/...dear-library-of-congress.html

eresources_study

shared by Lisa Spiro on 15 Jan 09 - Cached

Cynthia Gillespie on 11 Feb 09

While interesting, I think this can be deleted as it doesn't focus on the feasibility of an all-digital library.

<div class="cArrow"> </div><div class="cContentInner">While interesting, I think this can be deleted as it doesn't focus on the feasibility of an all-digital library.</div>

...

Cancel

Digital Repositories Foment a Quiet Revolution in Scholarship - Technology - The Chroni... - 2 views

chronicle.com/...65894

openaccess institutionalrepository publishing economic cultural repositories

shared by Geneva Henry on 21 Jun 10 - Cached

David Mimno - Publications - 0 views

www.cs.umass.edu/...publications.html

technical discovery

shared by Geneva Henry on 29 Jan 09 - Cached

Lisa Spiro on 29 Jan 09

BROWSING VIRTUALLY

<div class="cArrow"> </div><div class="cContentInner">BROWSING VIRTUALLY</div>

...

Cancel
Lisa Spiro on 29 Jan 09

"Organizing the OCA: Learning faceted subjects from a library of digital books. David Mimno and Andrew McCallum. Joint Conference on Digital Libraries (JCDL) 2007, Vancouver, BC, Canada. PDF The Open Content Alliance is one of several large-scale digitization projects currently producing huge numbers of digital books. Statistical topic models are a natural choice for organizing and describing such large text corpora, but scalability becomes a problem when we are dealing with multi-billion word corpora. This paper presents a new method for topic modeling, DCM-LDA. In this model, we train an independent topic model for every book, using pages as "documents". We then gather the topics discovered, cluster them, and then fit a Dirichlet prior for each topic cluster. Finally, we retrain the individual book topic models using these new shared topics. " via Dan Cohen working on virtual shelves project, using information within texts (OCA) as organizing principle instead of LCSH; former Perseus programmer

<div class="cArrow"> </div><div class="cContentInner"> "Organizing the OCA: Learning faceted subjects from a library of digital books. David Mimno and Andrew McCallum. Joint Conference on Digital Libraries (JCDL) 2007, Vancouver, BC, Canada. PDF The Open Content Alliance is one of several large-scale digitization projects currently producing huge numbers of digital books. Statistical topic models are a natural choice for organizing and describing such large text corpora, but scalability becomes a problem when we are dealing with multi-billion word corpora. This paper presents a new method for topic modeling, DCM-LDA. In this model, we train an independent topic model for every book, using pages as "documents". We then gather the topics discovered, cluster them, and then fit a Dirichlet prior for each topic cluster. Finally, we retrain the individual book topic models using these new shared topics. " via Dan Cohen working on virtual shelves project, using information within texts (OCA) as organizing principle instead of LCSH; former Perseus programmer</div>

...

Cancel