Thursday 15 December 2011
Seeks, Collaborative Search Solutions
Thursday, December 15th, 2011 at 11:00AM
Speaker: Emmanuel Benazera
, CEO & Founder at Seeks
, Toulouse, France
He will expose the range of problems and challenges that arise in building collaborative search solutions, as well as the architecture and range of innovative technologies we employ to solve them.
|
|
Monday 05 December 2011
Disjoint paths, multiflows, and applications in chip design
Jens Vygen
, Professor,University of Bonn
, Bonn, Germany.
Many applications (including routing problems) can be modeled by vertex- or edge-disjoint paths in directed or undirected graphs. The resulting optimization problems are NP-hard in general, but can be solved efficiently in some special cases. Otherwise the fractional relaxation (multiflows) often helps. I will explain why, what distinguishes it from single-commodity flows, and how to solve it. I will also discuss real-world applications to the layout of digital chips.
|
|
Wednesday 23 November 2011
Rich prior knowledge in learning for natural language processing
|
João Graça
, Researcher,Institute for Systems and Computer Engineering (INESC)
, Lisbon, Portugal.
We possess a wealth of prior knowledge about most prediction problems, and particularly so for many of the fundamental tasks in natural language processing. Unfortunately, it is often difficult to make use of this type of information during learning, as it typically does not come in the form of labeled examples, may be difficult to encode as a prior on parameters in a Bayesian setting, and...
Click to watch the video
|
|
|
|
Friday 18 November 2011
Artistic Stylization and Sketch based Search of Visual Media Collections
|
|
Thursday 10 November 2011
Bayesian Tools for Computational Linguistics
Thursday, November 10th, 2011 at 11 AM
Speaker: Yee Whye Teh
, Lecturer at University College London
, London, U.K.
He will discuss that prior distributions can be powerful ways to put computational linguistics knowledge into models.
|
|
Thursday 03 November 2011
Nonparametric bayesian models for structured objects
Zoubin Ghahramani
, Professor, University of Cambridge, Cambridge, U.K., Adjunct Faculty, University College London, London, U.K.
Bayesian nonparametrics provides an elegant framework for developing flexible models for machine learning and statistics. Much work has been done on nonparametric models of distributions (e.g. Dirichlet processes) and functions (e.g. Gaussian processes). However, many modelling tasks require latent variables with richer structures. I will describe our recent work on sparse matrices and graph structures (via the Indian Buffet Process), on hierarchies (via the Pitman-Yor Diffusion Tree), on models of covariance matrices (via the Wishart process), and on network structured regression.
Joint work with Ryan P. Adams, Tom Griffiths, David K. Knowles, Hanna M. Wallach, and Andrew G. Wilson.
|
|
Friday 21 October 2011
From narratives to conventions leveraging textual annotations to empower end-users in collaboration
| Carla Simone
, professor, Universita di Milano Bicocca, Milan, Italy.
In the last years our research focused on collaboration mediated by documental artifacts in different domains, among which the healthcare domain. In the observed practices, paper-based documental artifacts are often augmented by various kinds of annotations to convey additional information for various purposes. A technology aimed at supporting this natural behaviour should consider the aim of annotations in relation to the contents of the documental artifact they refer to in order to provide the user with the appropriate functionality...
Click to watch the video
|
|
|
|
Thursday 20 October 2011
Implicit linguistic entities and the problem of coreference resolution
| Rodolfo Delmonte
, Professor, Università Cà Foscari, Venezia, Italy.
In my talk I will introduce the problem of the recovery of implicit linguistic entities in the context of coreference resolution in open domain texts, which can be regarded as the most important task to cope with in either IR/IE or Q/A. I will present attempts at solving it and experiments reported in the literature of NLP and in particular computational linguistics...
click to watch the video
|
|
|
|
Friday 14 October 2011
Intelligent Mobile Assistance to Support Grocery Shopping
October 14th, 2011 - 11:00AM
Petteri Nurmi
,
University of Helsinki, Finland, will present work on developing support for mobile grocery assistance focusing particularly on recommendation techniques that work on top of natural language shopping lists and location-based services for inside the store.
XRCE seminars
|
|
Thursday 29 September 2011
Mining Social Networks: Principles and Applications
Thursday, September 29th, 2011 at 11.00am
Hakim Hacid
, researcher, Bell Labs Alcatel-Lucent, Nozay, France, will talk about the usage of social knowledge to solve issues in other areas.
XRCE seminars
|
