CFP (May 9): Big Data Mining Workshop (BigMine-12) at KDD12

Big Data Mining
1st International Workshop on Big Data, Streams and Heterogeneous
Source Mining: Algorithms, Systems, Programming Models and
Applications (BigMine-12)

Conference Dates: August 12-16, 2012
Workshop Date: Aug 12, 2012
Beijing, China

http://www.big-data-mining.org

Key dates:
Papers due: May 9, 2012
Acceptance notification: May 23, 2012
Workshop Final Paper Due: June 8, 2012
Workshop Proceedings Due: June 15, 2012

Paper submission and reviewing will be handled electronically. Authors
should consult the submission site (http://
http://big-data-mining.org/submission/) for full details regarding
paper preparation and submission guidelines.

Papers submitted to BigMine-12 should be original work and
substantively different from papers that have been previously
published or are under review in a journal or another
conference/workshop.

Following KDD main conference tradition, reviews are not double-blind,
and author names and affiliations should be listed.

We invite submission of papers describing innovative research on all
aspects of big data mining.

Examples of topic of interest include

1. Scalable, Distributed and Parallel Algorithms
2. New Programming Model for Large Data beyond Hadoop/MapReduce,
STORM, streaming languages
3. Mining Algorithms of Data in non-traditional formats (unstructured,
semi-structured)
4. Applications: social media, Internet of Things, Smart Grid, Smart
Transportation Systems
5. Streaming Data Processing
6. Heterogeneous Sources and Format Mining
7. Systems Issues related to large datasets: clouds, streaming system,
architecture, and issues beyond cloud and streams.
8. Interfaces to database systems and analytics.
9. Evaluation Technologies
10. Visualization for Big Data
11. Applications: Large scale recommendation systems, social media
systems, social network systems, scientific data mining,
environmental, urban and other large data mining applications.

Papers emphasizing theoretical foundations, algorithms, systems,
applications, language issues, data storage and access, architecture
are particularly encouraged.

We welcome submissions by authors who are new to the data mining
research community.

Submitted papers will be assessed based on their novelty, technical
quality, potential impact, and clarity of writing. For papers that
rely heavily on empirical evaluations, the experimental methods and
results should be clear, well executed, and repeatable. Authors are
strongly encouraged to make data and code publicly available whenever
possible.

Top-quality papers accepted and presented at the workshop after
careful revisions by the authors, reviewed by original PC members and
chairs will be recommended to ACM TIST, ACM TKDD, IEEE Intelligent
Systems or IEEE Computer for fast publication, depending on relevance
of the topic

Vision and sports summer school 2012 – application closes May 15th

_______________________

Application closes May 15th
_________________________

VISION AND SPORTS SUMMER SCHOOL

Prague, 27-31 August 2012

http://cmp.felk.cvut.cz/summerschool2012/
email: vs3@cmp.felk.cvut.cz

application deadline: 15 May 2012

Organized in collaboration with NIFTi
http://www.nifti.eu

OVERVIEW

Vision and Sports is a special special kind of summer school. In
addition to a broad-range of lectures on state-of-the-art Computer
Vision techniques, it offers exciting sport activities, such as
Tennis, Archery, Kung-Fu and Ultimate Freesbee. Sports are organized
by the same internationally renowned experts who deliver the lectures.
The school offers the best of both worlds to participants:
high-quality teaching on Computer Vision, and lots of fun with a
variety of attractive sports. This offers plenty of opportunity for
personal contact between students and teachers.

The Vision and Sports Summer School covers a broad range of subjects,
reflecting the diversity of Computer Vision. Each lecture will cover
both basic aspects and state-of-the-art research. Every day there are
two Computer Vision classes and one sports session. The classes
include both lectures and practical exercises.

The school is open to about 60 participants, and is targeted mainly to
young researchers (Master students and PhD students in particular).

Following the 5-day summer school, there will be a robotic workshop
organized by the EU project NIFTi (www.nifti.eu). The participants
will apply vision algorithms on the NIFTi mobile robot(s) and move the
robot around using the Ladybug3 camera the robot is equipped with.
Attendance to this workshop is optional and limited to a small number
of attendees. http://cmp.felk.cvut.cz/niftivisionworkshop2012/

TEACHERS

Jiri Matas
Czech Technical University

Phil Torr
Oxford Brookes University

Carsten Rother
Microsoft Research Cambridge

Christoph Lampert
IST Austria

Patrick Perez
Technicolor Research and Innovation

Silvio Savarese
University of Michigan

Vittorio Ferrari
University of Edinburgh

Bastian Leibe
RWTH Aachen University

Ondrej Chum
Czech Technical University

COMPUTER VISION LECTURES

Current list of topics:

Local feature extraction
Large-scale specific object recognition
Single-view and multi-view object categorization
MRF/CRF in Computer Vision
Semantic segmentation
Weakly supervised learning of visual models
Kernel Methods in Computer Vision
Tracking in video

SPORT ACTIVITIES

Tennis, Volleyball, Unihockey, Archery, Table Tennis, Soccer, Archery,
Ultimate Freesbee, Kung-Fu, Basketball, Tai chi, Badminton

APPLICATION

The school is open to about 60 participants. Please apply online at

http://cmp.felk.cvut.cz/summerschool2012/

Although priority will be given to young researchers (Master/PhD
students in particular), applications from senior researchers and
industrial professionals are welcome as well. The registration fee for
PhD students is only 300 Euro. This fee includes all classes, sports
activities, coffee breaks, lunches, and a social dinner. For hotel
accommodation, students will get discount rates on hotels affiliated
with the school.

Applicants should apply before 15 May 2012.
Notification of acceptance will be sent by 31 May 2012.

MORE INFORMATION

http://cmp.felk.cvut.cz/summerschool2012/

Deadline extension May 16: Object, functional, structured data ICML 2012 Workshop

2nd CALL FOR CONTRIBUTIONS

Object, functional, structured data : towards next generation kernel-based methods

ICML 2012 Workshop, June 30, 2012, Edinburgh, UK.

https://sites.google.com/site/nextgenkernels/

Important dates

Submission due by May 16, 2012.

Author Notification, May 21, 2012.

Workshop, June 30, 2012.

Topic

This workshop concerns analysis and prediction of complex data such as objects, functions and structures. It aims to discuss various ways to extend machine learning and statistical inference to these data and especially to complex outputs prediction. A special attention will be paid to operator-valued kernels and tools for prediction in infinite dimensional space.

Context and motivation

Complex data occur in many fields such as bioinformatics, information retrieval, speech recognition, image reconstruction, econometrics, biomedical engineering. In this workshop, we will consider two kinds of data: functional data and object or structured data. Functional data refers to data collected under the form of sampled curves or surfaces (longitudinal studies, time series, images). Analysis of these data as samples of random functions rather that a collection of individual observations is called Functional Data Analysis (FDA). FDA involves statistics in infinite-dimensional spaces and is closely associated to operatorial statistics. Its main approaches include functional principal component analysis and functional regression. Many theoretical challenges remain open in FDA and attract an increasing number of researchers.

Object and structure data exhibit an explicit structure like trees, graphs or sequences. For instance, documents, molecules, social networks and again images can be easily encoded as objet structured data. For the two last decades, both machine learning and statistics communities have developed various approaches such as graphical probabilistic models as well as kernel methods to take into account the structure of the data. In the meantime, FDA has been extended to Object Data Analysis which deals with samples of object data.

However, most of the efforts have been concentrated so far on dealing with complex inputs. In this workshop, we would like to emphasize the problem of complex outputs prediction which is involved for instance in multi-task learning, structured classification and regression, and network inference. All these tasks share a common feature: they can be viewed as approximation of vector-valued functions instead of scalar-valued functions and in the most general case, the output space is an Hilbert space. A promising direction first developed in (Micchelli and Pontil, 2005) consists in working with Reproducing Kernel Hilbert Spaces with operator-valued kernels in order to get an appropriate framework for regularization. There is thus a strong link between recent works in machine learning about prediction of multiple or complex outputs and functional and operatorial statistics.

This workshop aims at bringing together researchers from both communities to 1) provide an overview of existing concepts and methods, 2) identify theoretical challenges and (3) discuss practical applications and new tasks.

Invited speakers

Yasemin Altun (Google)

Frédéric Ferraty (University of Toulouse, France)

Arthur Gretton (Gatsby Unit, UCL MPI for Intelligent Systems, UK)

Neil Lawrence (University of Sheffield, UK)

Steve Marron (University of North Carolina, USA)

Charles Micchelli (University of Albany, USA)

Call for contributions

We invite short, high-quality submissions on the following topics:

* complex output learning
* structured output prediction
* functional data analysis

* object data analysis
* operator-valued kernels

* operator-based statistics

* joint-kernel maps
* statistical dynamics
* applications (non exhaustive list) : signal and image processing, bioinformatics, natural language processing, time series modeling …

Submission guidelines

Submissions should be written as extended abstracts, no longer than 4 pages in the ICML latex style. ICML style files and formatting instructions can be found at The submissions should include the authors’ name and affiliation since the review process will not be double blind. The extended abstract may be accompanied by an unlimited appendix and other supplementary material, with the understanding that anything beyond 4 pages may be ignored by the program committee. Please send your submission by email to nextgenkernelicml2012@gmail.com before May 7, 2102 at midnight PDT. Recently-published work is allowed.

We expect to select contributions for the spotlight and poster sessions. Authors will receive a notification by May 21, 2012.

Organizers

Florence d’Alché-Buc (University of Evry & INRIA-Saclay, France)
Hachem Kadri (INRIA-Lille, France)
Massimiliano Pontil (University College London, UK)
Alain Rakotomamonjy (University of Rouen, France)

Website admin: Céline Brouard (University of Evry, France)
Contact: nextgenkernelicml2012@gmail.com

Summer School on Domain Adaptation

Summer School on Domain Adaptation in Image Analysis:

The Summer School will be held in Copenhagen, Denmark from August 20-24th 2012. The school will present basic and advanced topics in domain adaptation through theoretical and practical lectures given by distinguished researchers in the field, among them Corinna Cortes, Mehryar Mohri, Yishay Mansour, and Trevor Darrell. All of them have strong experience in the topic of the Summer School. In addition, there will be lectures given by local members of the research group at DIKU.

We expect that the students finish the course with an apprehension of the variety of domain adaptation methods, and that they have been given the tools to tackle this learning problem in their own work. The lectures will be supplemented with practical exercises to deepen the students’ understanding of the material. In a plenum session, the invited experts will discuss future perspectives for the methods.

For further information, please visit the homepage of the Summer School (http://image.diku.dk/MLLab/SummerSchools/index.html). We hope to welcome you in Copenhagen.

Last call for papers – Eleventh International Symposium on Intelligent Data Analysis (IDA 2012)]

— — — — — — — — — — — — — — — —

Dear colleagues,

The Eleventh International Symposium on Intelligent Data Analysis
(IDA 2012) will be organized in Helsinki, Finland during 25-27 October,
2012. The call for papers is found at: http://ida2012.org/cfp.html

We are quickly approaching the submission deadline on May 12, 2012.

The submission system is open. The format of submissions is 11 pages
in the Springer LNCS format. More detailed information and the link
to the submission system can be found on: http://ida2012.org/submission.html

You may also follow news and updates on IDA 2012 in Twitter:
http://twitter.com/ida_news

On behalf of the IDA 2012 organizers,
Jaakko Hollmén

* * * * * * * * * * * * * * * * * * * * * * * * * * * *

CALL FOR PAPERS

The Eleventh International Symposium on
Intelligent Data Analysis (IDA 2012)

October 25-27, 2012, Helsinki, Finland

http://ida2012.org

* * * * * * * * * * * * * * * * * * * * * * * * * * * *

When the IDA symposium series started in 1995, it focussed on the
problem of end-to-end intelligent support for data analysis. In
2010, the IDA symposium re-focussed to support papers that go
beyond established technology and offer genuinely novel and
“game-changing” ideas, whilst not always being as fully realised as
papers submitted to other conferences. IDA 2012 continues this
approach and will include an important and still emerging class of
problems: the analysis of data from networked digital information
systems such as mobile devices, remote sensors, streaming
applications (e.g. Twitter), etc.

The IDA symposium seeks “first look” papers that might elsewhere be
considered preliminary but contain potentially high impact
research. The IDA symposium, which is A-ranked according to ERA, is
open to all kinds of modelling and analysis methods, irrespective
of discipline. It is expected to be an interdisciplinary meeting
that seeks abstractions that cut across domains. IDA 2012 welcomes
papers that focus on dynamic and evolving data, models, and
structures and the analysis of data from digital environments.

FRONTIER PRIZE

In line with the theme of IDA 2012, the IDA Frontier Prize will be
awarded to the most visionary contribution. Submissions considered
for this award must present novel and surprising approaches to data
analysis. The award consists of a plaque and a prize of 1000 Euros.

CALL FOR PAPERS

IDA solicits papers on all aspects of intelligent data analysis,
including papers on intelligent support for modelling and analyzing
data from complex, dynamical systems. IDA 2012 particularly
encourages papers about:

– Novel applications of IDA techniques to, e.g., digital environments
– Novel modes of data acquisition and the associated issues
– Robustness and scalability issues of intelligent data analysis techniques
– Visualization and dissemination of results

Intelligent support for data analysis goes beyond the usual
algorithmic offerings in the literature. Papers about established
technology will only be accepted if the technology is embedded in
intelligent data analysis systems, or is applied in novel ways to
analyzing and/or modelling complex systems.

The conventional reviewing process, which favours incremental
advances on established work, can discourage the kinds of papers
that IDA 2012 hopes to publish. The reviewing process will address
this issue explicitly: referees will evaluate papers against the
stated goals of the symposium, and any paper for which at least one
program chair advisor writes an informed, thoughtful, positive
review will be accepted irrespective of other reviews.

The proceedings of IDA 2012 will appear in Springer’s Lecture Notes
in Computer Science (LNCS) series. For more details on submission
and review process, see the IDA webpage at http://www.ida2012.org
or contact the program chairs. News and updates will be posted on the
IDA Twitter account @ida_news.

IMPORTANT DATES

Deadline for submissions: 12 May, 2012
Author notification: 14 July, 2012
Camera-ready papers due: 11 August, 2012
Conference dates: 25-27 October, 2012

INVITED SPEAKERS

Paola Sebastiani, Boston University, USA
Arno Siebes, University of Utrecht, The Netherlands
Gavin Cawley, University of East Anglia, United Kingdom

ORGANIZATION

General Chair:
Jaakko Hollmen, Aalto University, Finland

Program Chairs:
Frank Klawonn, Ostfalia University of Applied Sciences, Germany
Allan Tucker, Brunel University, United Kingdom

Poster Chair:
Frank Hoppner, Ostfalia University of Applied Sciences, Germany

Frontier Prize Chairs:
Elizabeth Bradley, University of Colorado, United States
Joao Gama, University of Porto, Portugal

ECML PKDD 2012: Last Call for Demos and NECTAR-track submissions

ECML PKDD 2012: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
September 24-28, 2012 – Bristol, UK

Home

———————————————–
Call for Demonstrations
———————————————–

ECML PKDD 2012 solicits submissions for demos. Submissions must describe working systems and be based on state-of-the-art machine learning and data mining technology. These systems may be innovative prototype implementations or mature systems that use machine learning techniques and knowledge discovery processes in a real setting. We particularly welcome demos that use open-source software. For more information, please check http://www.ecmlpkdd2012.net/calls/call-for-demos/

Submission deadline: Friday, May 18, 2012

All aspects of the submission and notification process will be handled online via the CMT conference management toolkit at https://cmt.research.microsoft.com/ECMLPKDD2012/

For inquiries please contact us at ECMLPKDD2012demos@cs.bris.ac.uk

Bettina Berendt & Myra Spiliopoulou
ECML PKDD 2012 Demo Track Chairs

———————————————–
Call for NECTAR-track submissions
———————————————–

For the first time, ECML PKDD 2012 will have a NECTAR-track, featuring significant machine learning and data mining results published or disseminated no earlier than 2010 at a different conference or in a journal. One goal of this track is to offer conference attendees the opportunity to learn about machine learning and/or data mining related results published in other communities. Papers describing innovative applications of state-of-the-art machine learning and/or data mining algorithms are also welcome, but should be different from demonstration papers; the latter are to be submitted to the demos track. We also invite submissions presenting compactly well-founded results which appeared in a series of publications that advanced a single novel influential idea or vision. For more information, please check: http://www.ecmlpkdd2012.net/calls/call-for-nectar-talks/

Submission deadline: Friday, May 18, 2012

All aspects of the submission and notification process will be handled online via the CMT conference management toolkit at https://cmt.research.microsoft.com/ECMLPKDD2012/

For inquiries please contact us at ECMLPKDD2012nectar@cs.bris.ac.uk

Thomas Gaertner & Gemma Garriga
ECML PKDD 2012 NECTAR Track Chairs

ECML PKDD 2012: Last Call for Demos and NECTAR-track submissions

ECML PKDD 2012: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
September 24-28, 2012 – Bristol, UK

Home

———————————————–
Call for Demonstrations
———————————————–

ECML PKDD 2012 solicits submissions for demos. Submissions must describe working systems and be based on state-of-the-art machine learning and data mining technology. These systems may be innovative prototype implementations or mature systems that use machine learning techniques and knowledge discovery processes in a real setting. We particularly welcome demos that use open-source software. For more information, please check http://www.ecmlpkdd2012.net/calls/call-for-demos/

Submission deadline: Friday, May 18, 2012

All aspects of the submission and notification process will be handled online via the CMT conference management toolkit at https://cmt.research.microsoft.com/ECMLPKDD2012/

For inquiries please contact us at ECMLPKDD2012demos@cs.bris.ac.uk

Bettina Berendt & Myra Spiliopoulou
ECML PKDD 2012 Demo Track Chairs

———————————————–
Call for NECTAR-track submissions
———————————————–

For the first time, ECML PKDD 2012 will have a NECTAR-track, featuring significant machine learning and data mining results published or disseminated no earlier than 2010 at a different conference or in a journal. One goal of this track is to offer conference attendees the opportunity to learn about machine learning and/or data mining related results published in other communities. Papers describing innovative applications of state-of-the-art machine learning and/or data mining algorithms are also welcome, but should be different from demonstration papers; the latter are to be submitted to the demos track. We also invite submissions presenting compactly well-founded results which appeared in a series of publications that advanced a single novel influential idea or vision. For more information, please check: http://www.ecmlpkdd2012.net/calls/call-for-nectar-talks/

Submission deadline: Friday, May 18, 2012

All aspects of the submission and notification process will be handled online via the CMT conference management toolkit at https://cmt.research.microsoft.com/ECMLPKDD2012/

For inquiries please contact us at ECMLPKDD2012nectar@cs.bris.ac.uk

Thomas Gaertner & Gemma Garriga
ECML PKDD 2012 NECTAR Track Chairs

Job in Machine Translation: 2-year research position at Sheffield University

The Department of Computer Science has a position for a Research
Associate in Machine Translation. The position is funded by the EU FP7
as part of the QTLaunchPad project, which will investigate how to
measure and overcome quality barriers in Machine Translation (MT).

QTLaunchPad is a support action which aims at producing a better
environment for large-scale collaborative research on high-quality MT,
and preparing and launching a large international action dedicated to
a scientifically and economically significant breakthrough in quality
translation technology. Key to this project are the methodological
and empirical foundations of research toward breaking the
quality-barriers. As a partner in this project, the University of
Sheffield will be primarily responsible for the Quality Estimation
methods and software and its use for guiding MT, but will also
contribute to the analysis of quality barriers and design of quality
metrics.

At the University of Sheffield the project will be led by Dr Lucia
Specia (http://www.dcs.shef.ac.uk/~lucia/). The research will build
upon the group’s leading research in statistical modelling of the
quality estimation problem. It will employ a Research Associate for up
to 24 months, available to start July 2012. The role will require the
post holder to undertake research and software development on quality
estimation, and to collaborate with other researchers working on the
QTLaunchPad Project (Sheffield, DCU-Dublin, DFKI-Saarbrücken and
ILSP-Athens).

This is an opportunity to work in a well-connected international team
with world-leading reputations in the Natural Language Processing
(NLP) research group at The University of Sheffield. The NLP group is
well known internationally for its research, and is one of the largest
research groups in computational linguistics and text engineering in
the UK. There are excellent opportunities for publications, project
and conference trips. For suitably qualified candidates, possibilities
exist to contribute to teaching, for example as part of an MSc in
Computer Science with Speech and Language Processing.

Applicants should have:

– PhD (or equivalent work experience) in a related area
– Experience in natural language processing
– Acquaintance with Machine Translation
– Programming experience, e.g., in C++ , Java, Perl/Python

Experience in machine learning, experience in evaluation of machine
translation and multilingual background (English and especially one of
the following languages of the Project: Portuguese, Greek, or German)
are a plus.

Salary for this grade: £28,401 – £35,938 per annum with potential to
progress to £37,012 per annum.

For informal inquiries contact Dr. Lucia Specia: L.Specia@sheffield.ac.uk

For applications: http://www.shef.ac.uk/jobs, Search and apply for
jobs using reference number UOS004520

Closing date: 25 May 2012.

Call for Paper: Special Issue on NLP in the Web Era

Call for paper

Special issue on
Natural Language Processing in the Web Era

Intelligenza Artificiale, Volume 6.2, scheduled for December 2012

Guest editors: Roberto Basili and Bernardo Magnini

THEMES

Natural Language is still the main carrier for the definition, synthesis and exchange of knowledge in the real world,
and this is entirely reflected in the Web contents. Although the growing levels of integration, multichannel and
modalities of the information made available in the current Web, thus including the Social Web bodies of resources,
the central role of language in e-mails, blogs, twits as well as multimedia pages cannot be denied.
Notice that even for pictures, videos or audio information (including news or artistic materials) natural language is
crucial in the annotation, explanation and delivery processes.

Unfortunately, the increase in volumes also corresponds to a growing complexity in terms of needs,
phenomena and applications. While social media often introduce specific sublanguages that are still largely
unexplored by current language processing tools, the pervasive noise and incompleteness that characterize
real documents in blogs, forums or SMS channels also amplify requirements such as coverage and robustness
of the NLP technology. On the other side, while knowledge representation technologies require massive amount
of Web data to be traced, linked and semantically harmonized, this enterprise is tightly bound by the quality
of the linguistic interpretation capabilities that the underlying integration systems can exhibit. Finally, the forms
of information retrieval, exchange and sharing used commonly by large communities of Social Web users
are such that the semantic management of smaller text units is crucially needed. Specific tasks, such as
personalized document management or context-aware search in mobile applications are strongly tight to the
interpretation of fine-grain phenomena, such as questions, short queries or twits. In these large scale distributed
scenarios multilinguality is also an issue for language processing technologies.

The above challenges and the topics related to research advances in this area are all central to this special issue.
Original research papers as well as surveys of on-going work in specific sectors are welcomed.
The aim is to provide to researchers both in the academic and industrial sectors a comprehensive picture of a
largely multidisciplinary field. We are soliciting contributions related to the following, not exhaustive, set of themes:

– Semantic Web. Language processing for open linked data. Linguistic approaches to Ontology Learning, Reconciliation
and Population. Language Processing for Ontology Engineering. Semantic Web applications with explicit language
processing components.
– Search. Question Answering. Lexical Semantic approaches to Intelligent Web Search. Semantic search.
Enterprise Search. The use of Lexical Resources for Knowledge Search in the Web.
– Language and Learning. Computational Natural Language Learning from Web data. Machine Learning methods,
models and algorithms for treating linguistic information implicit in Web data. Advanced Supervised learning for NLP.
Semi-supervised and Unsupervised approaches for NLP over the Web.
– Web, Linguistic Resources and Knowledge Acquisition. Wikipedia-based knowledge acquisition. Machine
Reading from Web sources. Web-scale Information Extraction.
– Multimodality. Human-Computer Interfaces. Speech and Language based interface. Multimodal Interaction.
Digital assistants. Language-based Mobile and Web applications.
– Social media. New languages of the Social Web. Linguistic Treatment of Social Web data. Special-purpose
lexical and grammatical models for Web 2.0 languages.
Folksonomies and Language Processing. Lexical knowledge and Cloud Tags.
– Sentiment Analysis, Emotion Modeling and Recommending. Language Processing approaches to
Opinion Analysis. Emotional computing. Digital Advertisement and Persuasion.

PRELIMINARY REVIEWING COMMITTEE

Marie Helene Candito, Universite Paris 7
Philipp Cimiano, University of Bielefeld
Rodolfo Delmonte, University of Venice
Gregory Grefenstette, 3DS Exalead, France
Iryna Gurevych, University of Darmstadt
Leonardo Lesmo, University of Turin
Rutu Mulkar-Mehta, University of California, San Diego
Guenter Neumann, DFKI, Germany
Sergei Nirenburg, University of Maryland
Massimo Poesio, University of Trento, Italy
German Rigau, University of the Basque Country
Frederique Segond, Viseo, France
Giovanni Semeraro, University of Bari
Anne Vilnat, Limsi, France
Yorick Wilks, Florida Institute of Human and Machine Cognition

IMPORTANT DATES

– Deadline for submission: June 15th, 2012
– List of papers selected: July 30th , 2012
– Deadline for camera ready papers: September 15th 2012
– Publication: December 2012

THE JOURNAL

Intelligenza Artificiale (http://www.iospress.nl/journal/intelligenza-artificiale/), edited by IOS Press, is the official
journal of the Italian Association for Artificial Intelligence (AI*IA). Intelligenza Artificiale publishes rigorously reviewed articles
(in English) in all areas of Artificial Intelligence, with a special attention to original contributions. It also publish assessments
of the state of the art in various areas of AI, and innovative system descriptions with appropriate evaluation.

PRACTICAL ISSUES

Contributions (around 15 pages, PDF format) should be sent by email to the two guest editors,
Bernardo Magnini (magnini@fbk.eu) and Roberto Basili (basili@info.uniroma2.it).

Detailed submission instructions are available on the Web site of the journal:
http://www.iospress.nl/journal/intelligenza-artificiale/.
The journal only publishes original contributions in English.

Web site: http://ai-nlp.info.uniroma2.it/basili/NLPiWE/SpecialIssueOnNLP_in_the_Web_era_CFP.html

Last Call For Papers – Special Issue on Learning Semantics in Machine Learning *** Deadline May 1st ***

**Overview**
A key ambition of AI is to render computers able to evolve and interact
with the real world. This can be made possible only if the machine is able
to produce an interpretation of its available modalities (image, audio,
text, etc.) which can abe used to support reasoning and taking appropriate
actions. Computational linguists use the term “semantics” to refer to the
possible interpretations of natural language expressions and there is
recent work in “learning semantics” – finding (in an automated way) these
interpretations. However, “semantics” are not restricted to the natural
language (and speech) modality, and are also pertinent to visual
modalities. Hence, knowing visual concepts and common relationships
between them would certainly provide a leap forward in scene analysis and
in image parsing akin to the improvement that language phrase
interpretations would bring to data mining, information extraction or
automatic translation, to name a few.

Progress in learning semantics has been slow mainly because this involves
sophisticated models which are hard to train, especially since they seem
to require large quantities of precisely annotated training data. However,
recent advances in learning with weak, limited and indirect supervision
led to the emergence of a new body of research in semantics based on
multi-task/transfer learning, on learning with semi/ambiguous/indirect
supervision or even with no supervision at all. Hence, this special issue
invites paper submissions on recent work for learning semantics of natural
language, vision, speech, etc.

Papers should address at least some of the following questions:
– How should meaning representations be structured to be easily
interpretable by a computer and still express rich and complex knowledge?
– What is a realistic supervision setting for learning semantics?
– How can we learn sophisticated representations with limited supervision?
– How can we jointly infer semantics from several modalities?

**Dates**
Submission deadline: **May 1, 2012**
First review results: July 30, 2012
Final drafts: September 30, 2012

**Submissions**
Papers must be submitted online, selecting the article type that indicates
this special issue. Peer reviews will follow the standard Machine Learning
journal review process. It is the policy of the Machine Learning journal
that no submission, or substantially overlapping submission, be published
or be under review at another journal or conference at any time during the
review process. Papers extending previously published conference papers
are acceptable, as long as the journal submission provides a significant
contribution beyond the conference paper, and the overlap is described
clearly at the beginning of the journal submission. Complete manuscripts
of full length are expected, following the MLJ guidelines in
http://www.springer.com/computer/ai/journal/10994 .

**Guest Editors**
Antoine Bordes (antoine.bordes@utc.fr)
Léon Bottou (leon@bottou.org)
Ronan Collobert (ronan@collobert.com)
Dan Roth (danr@illinois.edu)
Jason Weston (jweston@google.com)
Luke Zettlemoyer (lsz@cs.washington.edu)