BibSonomy publications for /author/GraberMon Jan 30 00:00:00 CET 2012SocialCom/PASSATconf/socialcom/2011734-737Simulating Audiences: Automating Analysis of Values, Attitudes, and Sentiment.2011dblp Fri Jan 20 00:00:00 CET 2012ICCV Workshopsconf/iccvw/2011708-711Online 3D reconstruction using convex optimization.2011dblp Thu Dec 15 00:00:00 CET 2011UAIconf/uai/200975-82Multilingual Topic Models for Unaligned Text.2009dblp Mon Dec 05 00:00:00 CET 2011CoRRSyntactic Topic Modelsabs/1002.46652010dblp Mon Dec 05 00:00:00 CET 2011CoRRUsing Variational Inference and MapReduce to Scale Topic Modelingabs/1107.37652011dblp Thu Nov 10 00:00:00 CET 2011NIPSconf/nips/2009288-296Reading Tea Leaves: How Humans Interpret Topic Models.2009dblp Thu Nov 03 00:00:00 CET 2011IEEE Trans. Med. Imaging168-77Optical Imaging of Anatomical Maps Derived from Magnetic Resonance Images Using Time-Independent Optical Sources.161997dblp Thu Nov 03 00:00:00 CET 2011IEEE Trans. Med. Imaging8852-866Imaging of spatiotemporal coincident states by DC optical tomography.212002dblp Fri Oct 28 00:00:00 CEST 2011IGARSSconf/igarss/20104079-4082A new scalloping filter algorithm for scansar images.2010dblp Fri Oct 28 00:00:00 CEST 2011IGARSSconf/igarss/20103059-3062Currents in rivers, coastal areas, and the open ocean from TerraSAR-X along-track InSAR.2010dblp Wed Oct 19 00:00:00 CEST 2011ISSCCconf/isscc/2009460-461A 2ns-read-latency 4Mb embedded floating-body memory macro in 45nm SOI technology.2009dblp Fri Jul 01 15:17:05 CEST 2011Weblogs und Wikis als Werkzeuge für das Wissensmanagement von KMU2007kmu usability wikis wissensmanagement Tue Jun 21 00:00:00 CEST 2011ACLconf/acl/2011248-257Interactive Topic Modeling.2011dblp Wed Jun 08 11:34:35 CEST 2011Reading Tea Leaves: How Humans Interpret Topic Models2010latent model predictive probabilistic space topic Probabilistic topic models are a popular tool for the unsupervised analysis of text, providing both a predictive model of future text and a latent topic representation of the corpus. Practitioners typically assume that the latent space is semantically meaningful. It is used to check models, summarize the corpus, and guide exploration of its contents. However, whether the latent space is interpretable is in need of quantitative evaluation. In this paper, we present new quantitative methods for measuring semantic meaning in inferred topics. We back these measures with large-scale user studies, showing that they capture aspects of the model that are undetected by previous measures of model quality based on held-out likelihood. Surprisingly, topic models which perform better on held-out likelihood may infer less semantically meaningful topics. 1Wed Jun 01 00:00:00 CEST 2011Med. Biol. Engineering and Computing2225-229Impedance-gradient electrode reduces skin irritation induced by transthoracic defibrillation.432005dblp Mon Apr 04 00:00:00 CEST 2011J. Comp. Assisted Learning170-84E-safety and Web 2.0 for children aged 11-16.252009dblp Mon Feb 21 00:00:00 CET 2011iConferenceconf/iconference/2011783-784Comparing values and sentiment using Mechanical Turk.2011dblp Mon Feb 21 00:00:00 CET 2011iConferenceconf/iconference/2011672-673Modeling diverse standpoints in text classification: learning to be human by modeling human values.2011dblp Thu Dec 16 15:59:01 CET 201075Würzburg Economic PapersHow to get tenured (in Germany, in Economics)2007Bibliometrie Publikationsverhalten Rankings Szientometrie Wirtschaftswissenschaften Zeitschriften Getting a tenured position in economics in Germany is viewed as a random outcome where the probability of tenure depends on the quantity and qual- ity of publications, age and years since PhD. We measure publications both in units of Top 5 journals and in units of the European Economic Review (EER). We …nd that the average age of a professor in the year of his …rst appointment in Germany in the period of 1970 to 2005 is 38. This is ap- proximately 8 years after the PhD. He has 1.5 “standardized”Top 5 papers or 2.2 “standardized”EER papers, i.e. written with one coauthor and of 20 pages length. Results vary across sub…elds and over time. Someone aiming for a tenured job after 2010 should by then (average over all …elds) have 3.3 standardized Top 5 papers or 5 standardized EER papers.Mon Dec 06 00:00:00 CET 2010BIOCOMPconf/biocomp/201055-61A Network-based Approach to Classify Disease Stages of Prostate Cancer Using Quantitative Network Measures.2010dblp