[UAI] TSD 2019 - Last Call for Papers

[TSD 2019]

**
  TSD 2019 - LAST CALL FOR PAPERS
**

   The twenty-second International Conference on
   TEXT, SPEECH and DIALOGUE (TSD 2019)
Ljubljana, Slovenia
   September 10-13, 2019
   http://www.tsdconference.org


IMPORTANT

The submission deadline March 31 is approaching. We will not extend the 
deadline.
However, in case you need some extra days, please let us know and do
the following: Register yourself and submit your paper with a valid abstract.
Put "UNFINISHED" as the first word in the abstract (both in the system 
and in the paper). We need at least the abstract to organize the reviews. 
When you finish your work, please, update the paper.  


TSD HIGHLIGHTS

* Keynote speakers:
Denis Jouvet (Loria, Nancy, France),
Aline Villavicencio (University of Essex, UK),
Bhiksha Raj (Carnegie Mellon University, USA),
Ryan Cotterell (University of Cambridge, UK).

* TSD is traditionally published by Springer-Verlag and regularly listed in
  all major citation databases: Thomson Reuters Conference Proceedings
  Citation Index, DBLP, SCOPUS, EI, INSPEC, COMPENDEX, etc.

* The TSD2019 conference is officially recognized as an INTERSPEECH 2019
  satellite event.

* The TSD2019 conference is supported by the International Speech
  Communication Association (ISCA). It holds the status of an ISCA
  Supported Event.

* TSD offers a high-standard transparent review process - double blind,
  final reviewers' discussion.

* TSD is going to take place in the beautiful centre of Ljubljana, the
  capital of Slovenia.

* The conference is organized in cooperation with the Faculty of Electrical
  Engineering, University of Ljubljana, Slovenia.

* TSD provides an all-service package (conference access and material, all
  meals, one social event, etc.) for an easily affordable fee.


IMPORTANT DATES

March 31, 2019 ... Deadline for submission of contributions
May 10, 2019 . Notification of acceptance or rejection
May 31, 2019 . Deadline for submission of camera-ready papers

September 10-13, 2019  TSD2019 conference date

The proceedings will be provided on flash drives in form of navigable
content. Printed books will be available for extra fee.


TSD SERIES

The TSD series has evolved as a prime forum for interaction between
researchers in both spoken and written language processing from all over
the world. Proceedings of the TSD conference form a book published by
Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI)
series. The TSD proceedings are regularly indexed by Thomson Reuters
Conference Proceedings Citation Index. LNAI series are listed in all major
citation databases such as DBLP, SCOPUS, EI, INSPEC, or COMPENDEX.


TOPICS

Topics of the 22nd conference will include (but are not limited to):

Speech Recognition (multilingual, continuous, emotional speech,
handicapped speaker, out-of-vocabulary words, alternative way of
feature extraction, new models for acoustic and language modeling).

Corpora and Language Resources (monolingual, multilingual, text, and
spoken corpora, large web corpora, disambiguation, specialized
lexicons, dictionaries).

Speech and Spoken Language Generation (multilingual, high fidelity
speech synthesis, computer singing).

Tagging, Classification and Parsing of Text and Speech (multilingual
processing, sentiment analysis, credibility analysis, automatic text
labeling, summarization, authorship attribution).

Semantic Processing of Text and Speech (information extraction,
information retrieval, data mining, semantic web, knowledge
representation, inference, ontologies, sense disambiguation, plagiarism
detection).

Integrating Applications of Text and Speech Processing (machine
translation, natural language understanding, question-answering
strategies, assistive technologies).

Automatic Dialogue Systems (self-learning, multilingual,
question-answering systems, dialogue strategies, prosody in dialogues).

Multimodal Techniques and Modeling (video processing, facial animation,
visual speech synthesis, user modeling, emotion and personality
modeling).


PROGRAMME COMMITTEE

All programme committee members are listed on the conference web pages
https://www.kiv.zcu.cz/tsd2019/index.php?page=committees


OFFICIAL LANGUAGE

The official language of the event is English, however, papers on issues
related to text and speech processing in languages other than English are
strongly encouraged.


LOCATION

Ljubljana, the Slovenian capital - a city, whose name means `The beloved',
is a great place to visit, although you will not find world renowned
attractions here. Nevertheless,

[UAI] PhD Position on Explainable Data Science using Formal Verification @Radboud University

[Nils Jansen]

Are you interested in improving the explainability of machine learning using 
formal verification? Are you interested in being a part of cutting edge 
research in cooperation with TNO and the iCIS institute at Radboud University, 
Nijmegen? Then apply for a PhD position within the EXoDuS project, where you 
will be jointly supervised by Dr. Nils Jansen (Radboud University, Nijmegen) 
and Dr. Guillermo Perez (University of Antwerp). 

* Responsibilities

As a PhD candidate, you will work on the project EXplainable Data Science using 
Formal Verification (EXoDuS). The project is partially funded by the VWDATA 
programme and the Institute for Computing and Information Science (iCIS) of 
Radboud University and will be carried out in close cooperation with TNO. 
  
The impact of artificial intelligence (AI) on autonomous driving, 
robot-assisted surgery, and home automation has resulted in an increased 
reliance on AI systems. In mission-critical applications, the inherent 
vulnerability of such systems to adversarial attacks poses a serious challenge. 
We propose to immerse humans in the process of robustifying AI systems against 
problems such as adversarial learning or data poisoning via formal methods. 
Formal verification in particular provides tools and algorithms to rigorously 
assess the correctness of a system. The key element is to enable humans to 
understand AI-made decisions in an adversarial environment. Decision-making is 
sufficiently captured by so-called strategies; a neural network, for example, 
represents a strategy that has been learned. For such strategies, data 
scientists and system engineers lack tools to answer transparency-related 
questions. 
 
You will use formal techniques and directions such as SMT solving, model 
checking, and partially observable Markov decision processes. From the AI 
perspective, you will marry the aforementioned concepts with (convolutional) 
deep neural networks and decision trees.

* Work environment

Strategically located in Europe, Radboud University is one of the leading 
academic communities in the Netherlands. The position is available in the 
Software Science group of the Institute for Computing and Information Sciences 
(iCIS) at Radboud University. Research at iCIS focuses on software science, 
digital security and data science. Our research mission is to improve the 
security and reliability of computer-based systems and algorithms through 
mathematically founded theories, methods and tools. During recent evaluations, 
iCIS has been consistently ranked as the No. 1 Computing Science department in 
the Netherlands. Evaluation committees praised our flat and open organisational 
structure, our ability to attract external funding, our strong ties to other 
disciplines, and our solid contacts with government and industrial partners. 
The Software Science group is well known for its contributions to the 
mathematical foundations of software, formal methods, and functional 
programming.

* Details

The application deadline is March 31, 2019. More information is available here: 
https://www.ru.nl/werken/details/details_vacature_0/?recid=601933 


For questions please contact Nils Jansen (n.jan...@science.ru.nl 
). 

* Further information

http://nilsjansen.org 

https://www.uantwerpen.be/en/staff/guillermoalberto-perez/ 


https://www.ru.nl/english/working-at/why-work-at-radboud-university-0/terms-employment/
 


https://commit2data.nl/en/vwdata 

https://www.ru.nl/icis/ 

https://www.tno.nl/en/ 

--
Dr. Nils Jansen
Assistant Professor
Department of Software Science
Radboud University Nijmegen
http://nilsjansen.org

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] [CFP] @ IJCAI 19: 14th Intl. Workshop on Neural-Symbolic Learning and Reasoning

[Doran, Derek]

CALL FOR PAPERS



14th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy’19) 
In conjunction with IJCAI 2019



https://sites.google.com/view/nesy19/



Submission deadline: Apr 12, 2019 anywhere on earth

Notification: May 10, 2019

Camera-ready paper due: May 24, 2019

IJCAI-19 conference: Aug 10-16, 2019



The NeSy workshop series is seen as a major venue for the presentation and 
discussion of key topics related to neural-symbolic computing. NeSy has 
provided an atmosphere for the free exchange of ideas and networking within the 
community of scientists that straddle the line between statistical and symbolic 
methods in AI. We invite theoretical and applied submissions of all types that 
span both connectionist and symbolic learning paradigms. We further invite 
papers detailing experimental and in-the-wild neural-symbolic systems and 
papers on topics where neural-symbolic learning has a strong use case.



Topics of interest include, but are not limited to, the following:



* Knowledge representation and reasoning in (deep) neural networks

* Symbolic knowledge extraction from neural and statistical learning models

* Explainable AI models, systems, and techniques that integrate connectionist 
and symbolic paradigms

* Neural-symbolic cognitive models

* Biologically-inspired neural-symbolic integration

* Continual learning, integration of logic and probabilities with neural 
networks

* Neural-symbolic methods for structured learning tasks, including transfer, 
meta, and relational learning

* Novel connectionist systems able to perform traditionally symbolic AI tasks 
(e.g., logical deduction)

* Novel symbolic systems able to perform traditionally connectionist tasks 
(e.g., unstructured data analysis)

* Applications in simulation, finance, robotics, the semantic web, software 
engineering, systems engineering, bioinformatics, and visual intelligence.



NeSy also invites short, clear, and well-written position papers for 
presentation and discussion during the workshop.



**Submission**



Researchers and practitioners are invited to submit original papers that have 
not been submitted for review or published elsewhere using the IJCAI paper 
style. Submitted papers must be written in English and should not exceed 6 
pages in the case of research and experience papers, or 3 pages in the case of 
position papers (including figures, bibliography and appendices). All submitted 
papers will be judged based on their quality, relevance, originality, 
significance, and soundness. Submissions need not be double-blind.



Submit your paper via: https://easychair.org/conferences/?conf=nesy19



Selected papers will be presented during the workshop. The workshop will 
include extra time for audience discussion of the presentation allowing the 
group to have a better understanding of the issues, challenges, and ideas being 
presented. Accepted papers will be published in official workshop proceedings, 
which will be distributed during the workshop. Authors of the best papers will 
be invited to submit a revised and extended version of their papers to the 
Journal of Applied Logics, College Publications.



General questions concerning the workshop should be addressed to 
a.gar...@city.ac.uk

For more information about neural-symbolic AI and the workshop series, please 
visit http://www.neural-symbolic.org/



Please join the NeSy mailing list 
n...@jiscmail.ac.uk which is used for general 
announcements about the workshop.

___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] ICLP 2019 - Research Challenges in Logic Programming Track

[Fioretto, Ferdinando]

The 35th International Conference on Logic Programming (ICLP 2019)
Research Challenges in Logic Programming Track

September 21-25, 2019
Las Cruces, New Mexico (USA)
https://www.cs.nmsu.edu/ALP/iclp2019/
-

Objectives

Are you a researcher in logic programming working on a problem that appears to 
be particularly challenging? Perhaps you feel a little stuck? Or, are you 
facing a problem that needs some LP technology you are not familiar with? Would 
you like to open a discussion for collaboration? The goal of the Research 
Challenges Track is to help researchers overcome their challenges by providing 
a venue to invite input from the broader community. Contributors to this less 
formal track will be given an opportunity to exchange ideas with other 
researchers who may have come up against, or are currently working on, similar 
problems. We hope the track will foster discussion and possibly even new 
collaborations.


Expected contributions

The Research Challenges Track at ICLP 2019  invites submissions describing LP 
research challenges in a wide range of areas, including but not limited to:

  *   Industry-level application of logic programming
  *   applications of logic programming to other sciences and AI 
(bioinformatics, natural language processing, digital forensics, etc.)
  *   logic programming and big data
  *   machine learning and logic programming
  *   logic programming and other computational paradigms
  *   theoretical foundations of logic programming


Evaluation and Feedback

In this track, the selection process will be less formal. While authors will 
receive some feedback, the review process will not be typical. We do not expect 
contributions only from seasoned researchers. Ph.D. students and junior 
researchers are more than welcome to contribute. Also, contributors outside the 
LP community will be given special attention. Any contribution that clearly 
describes a research problem relevant to logic programming will be evaluated 
positively. The chance to interact with other researchers during the conference 
will provide additional feedback and hopefully lead to a longer-term 
discussion/collaboration.


Important Dates (Tentative)


  *   Abstract registration and paper submission: July 15, 2019
  *   Notification: July 31, 2019
  *   Camera-ready copy: September 1, 2017
  *   Conference: September 21-25, 2019


Submission Details

All submissions must be written in English. Submissions should be no more than 
4 pages in OASIcs format, including references, and should describe a research 
problem or challenge. Accepted papers will be presented during the conference. 
Authors of accepted papers are expected to register to ICLP and present their 
work.


Any additional questions can be directed towards the Research Challenges Track 
Chairs:

Alessandro Dal Palu', Universita' di Parma
alessandro.dalp...@unipr.it

Amelia Harrison, Google
amelia.j.harri...@gmail.com

Joohyung Lee, Arizona State University
joo...@asu.edu
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] CFP AutoML @ ICML 2019

[Frank Hutter]

CALL FOR CONTRIBUTIONS

The ICML 2019 Workshop on Automated Machine Learning (AutoML 2019)

Collocated with ICML in Long Beach, June 14 or 15 (TBD), 2019

Web: http://icml2019.automl.org



*Important Dates:*

Submission deadline: 22 April 2019, 11:59pm UTC-12 (April 22 anywhere in
the world)

Notification: 17 May 2019



Workshop topic:
Machine learning has achieved considerable successes in recent years, but
this success often relies on human experts, who construct appropriate
features, design learning architectures, set their hyperparameters, and
develop new learning algorithms. Driven by the demand for off-the-shelf
machine learning methods from an ever-growing community, the research area
of AutoML targets the progressive automation of machine learning aiming to
make effective methods available to everyone. The workshop targets a broad
audience ranging from core machine learning researchers in different fields
of ML connected to AutoML, such as neural architecture search,
hyperparameter optimization, meta-learning, and learning to learn, to
domain experts aiming to apply machine learning to new types of problems.

We invite submissions on the topics of:

   - Model selection, hyper-parameter optimization, and model search
   - Neural architecture search
   - Meta-learning and transfer learning
   - Learning to learn new algorithms and strategies
   - Automation of any element of the ML pipeline, including:
  - feature extraction / construction
  - data cleaning
  - generation of workflows / workflow reuse
  - problem "ingestion" (from raw data and miscellaneous formats)
  - acquisition of new data (active learning, experimental design)
  - report generation (providing insight on automated data analysis)
  - selection of evaluation metrics / validation procedures
  - selection of algorithms under time/space/power constraints
  - construction of fair and unbiased machine learning models
  - semi-supervised and unsupervised machine learning
   - Extending the scope of AutoML towards automated data science
   - Human-in-the-loop approaches for AutoML
   - Demos of existing AutoML systems
   - Robustness of AutoML systems (w.r.t. randomized algorithms, data,
   hardware etc.)
   - Hyperparameter agnostic algorithms

We welcome submissions up to 6 pages in JMLR format (+ references). We
strongly encourage attachments of code to foster reproducibility;
reproducibility of results and easy availability of code will be taken into
account in the decision making process. All accepted papers will be
presented as posters. We may invite the best 2-3 papers for an oral plenary
presentation. Unless indicated by the authors, we will provide PDFs of all
accepted papers on http://icml2019.automl.org/. There will be no archival
proceedings. For submission details please see the submission page
.
Confirmed Keynote Speakers

   - Rachel Thomas
   - Raquel Urtasun
   - Charles Sutton

Tentative Dates

   - April 1st: submission system opens
   - April 22nd: submission deadline
   - May 17th: notification
   - June 14th or 15th: workshop day
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai