Send Moses-support mailing list submissions to
moses-support@mit.edu
To subscribe or unsubscribe via the World Wide Web, visit
http://mailman.mit.edu/mailman/listinfo/moses-support
or, via email, send a message with subject or body 'help' to
moses-support-request@mit.edu
You can reach the person managing the list at
moses-support-owner@mit.edu
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Moses-support digest..."
Today's Topics:
1. Call for Papers: DigitalSec2017 in Kuala Lumpur, Malaysia on
July 11-13, 2017 (Sandra Evans)
2. TSD 2017 - First Call for Papers (TSD 2017)
3. CFP: WMT 2017 *new* Shared Task on Bandit Learning for
Machine Tramslation (Artem Sokolov)
----------------------------------------------------------------------
Message: 1
Date: Thu, 26 Jan 2017 14:22:48 +0800
From: Sandra Evans <sandra.sdiwc@gmail.com>
Subject: [Moses-support] Call for Papers: DigitalSec2017 in Kuala
Lumpur, Malaysia on July 11-13, 2017
To: moses-support@mit.edu
Message-ID:
<CAEjUHKVe5+dun5unxBOFWESG9hy=7ib+PyjOuqo0NCN4zs8Udg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
------------------------------------------
CALL FOR PAPERS DigitalSec2017 - Malaysia
------------------------------------------
You are invited to participate in The Fourth International Conference on
Digital Security and Forensics (DigitalSec2017) that will be held in Kuala
Lumpur, Malaysia, on July 11-13, 2017. The event will be held over three
days, with presentations delivered by researchers from the international
community, including presentations from keynote speakers and
state-of-the-art lectures.
Website:
http://sdiwc.net/conferences/4th-conference-digital-security-forensics/
Email: digitalsec17@sdiwc.net
Submission Deadline: June 11, 2017
Submission Link:
http://sdiwc.net/conferences/4th-conference-digital-security-forensics/openconf/openconf.php
The conference welcome papers on the following (but not limited to)
research topics:
- Information and Data Management
- Social Networks
- Data Compression
- Information Content Security
- E-Technology
- Mobile, Ad Hoc and Sensor Network Management
- E-Government
- Web Services Architecture, Modeling and Design
- E-Learning
- Semantic Web, Ontologies
- Wireless Communications
- Web Services Security
- Mobile Networking, Mobility and Nomadicity
- Quality of Service, Scalability and Performance
- Ubiquitous Computing, Services and Applications
- Self-Organizing Networks and Networked Systems
- Data Mining
- Data Management in Mobile Peer-to-Peer Networks
- Computational Intelligence
- Data Stream Processing in Mobile/Sensor Networks
- Biometrics Technologies Indexing and Query Processing for Moving Objects
- Forensics, Recognition Technologies and Applications
- Cryptography and Data Protection
- Information Ethics
- User Interfaces and Usability Issues form Mobile Applications
- Fuzzy and Neural Network Systems
- Mobile Social Networks
- Signal Processing, Pattern Recognition and Applications
- Peer-to-Peer Social Networks
- Image Processing
- Sensor Networks and Social Sensing
- Distributed and parallel applications
- Social Search
- Internet Modeling
- Embedded Systems and Software
- User Interfaces,Visualization and Modeling
- Real-Time Systems
- XML-Based Languages
- Multimedia Computing
- Network Security
- Software Engineering
- Remote Sensing
Best Regards,
*Sandra Evans*
Conference Manager,
The Society of Digital Information and Wireless Communications (SDIWC)
20/F, Tower 5, China Hong Kong City,
33 Canton Road, Tsim Sha Tsui,
Kowloon, Hong Kong
Email: sdiwc@sdiwc.net
Phone Numbers :
from outside USA 001-202-657-4603
from Inside USA 202-657-4603
See more of the upcoming SDIWC Conferences at: www.sdiwc.net
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170126/d497d94a/attachment-0001.html
------------------------------
Message: 2
Date: Thu, 26 Jan 2017 09:56:31 +0100
From: TSD 2017 <xrambous@aurora.fi.muni.cz>
Subject: [Moses-support] TSD 2017 - First Call for Papers
To: tsd2017@tsdconference.org
Message-ID: <E1cWfr5-00042n-8e@aurora.fi.muni.cz>
**************************************************************************
TSD 2017 - FIRST CALL FOR PAPERS
**************************************************************************
The twentieth anniversary International Conference on
TEXT, SPEECH and DIALOGUE (TSD 2017)
Praha (Prague), Czech Republic
August 27-31, 2017
http://www.tsdconference.org
TSD HIGHLIGHTS
* Invited speakers: Tomas Mikolov (Facebook AI Research Group, USA), Lucia
Specia (The University of Sheffield, UK), Rico Sennrich (The University
of Edinburgh, UK) and other eminent personages with various expertise
related to the topics of the conference have been asked to give their
respective pieces of speech.
* 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.
* TSD offers high-standard transparent review process - double blind, final
reviewers discussion.
* The TSD2017 conference is supported by the International Speech
Communication Association (ISCA). It holds the status of an ISCA
Supported Event.
* TSD is officially recognized as an INTERSPEECH 2017 satellite event.
* TSD will take place in the historical centre of Prague, the Capital of
the Czech Republic.
* The conference is organized in co-operation with the Institute of Formal
and Applied Linguistics, Faculty of Mathematics and Physics of the
Charles University.
* TSD provides an all-service package (conference access and material, all
meals, one social event, etc.) for an easily affordable fee starting at
290 EUR for students and 360 EUR for full participants.
* Moreover, we succeeded in our effort to provide students with an
accommodation option for an affordable price of 20 EUR/night (+ 5 EUR for
the breakfast) in the nearby dormitories.
IMPORTANT DATES
March 31, 2017 ......... Deadline for submission of contributions
May 10, 2017 ........... Notification of acceptance or rejection
May 31, 2017 ........... Deadline for submission of camera-ready papers
August 27-31, 2017 ..... TSD2017 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
TSD series have 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 20th anniversary 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 modelling).
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 Modelling (video processing, facial
animation, visual speech synthesis, user modelling, emotion and
personality modelling).
PROGRAMME COMMITTEE
All programme committee members are listed on the conference web pages:
http://www.tsdconference.org/tsd2017/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.
CONFERENCE FEES
The conference fee depends on the date of payment and on the participant's
status (full or student). It includes one copy of the conference
proceedings (on a USB flash drive), refreshments/coffee breaks, lunches and
dinners, opening dinner, welcome party, mid-conference social event
admissions, and organizing costs. In order to lower the fee as much as
possible, the accommodation and the conference trip are not included in it
this time.
Full participant:
early registration by May 31, 2017 - CZK 10 000 (approx. 360 EUR)
late registration by August 1, 2017 - CZK 11 000 (approx. 400 EUR)
on-site registration - CZK 12 000 (approx. 444 EUR)
Student (reduced):
early registration by May 31, 2017 - CZK 8 000 (approx. 290 EUR)
late registration by August 1, 2017 - CZK 8 700 (approx. 322 EUR)
on-site registration - CZK 10 000 (approx. 360 EUR)
Dormitory accommodation 20 EUR/night (+ 5 EUR for the breakfast)
Please, keep in mind that the fees are preliminary and they may slightly
change in the future.
LOCATION
Praha (Prague)--also called The City of a Hundred Spires or The Heart of
Europe--is situated in the very centre of Bohemia on the banks of the river
Vltava. There live more than 1.2 million people in the metropolitan area.
Thus, Praha is considered the centre of science, higher education, culture,
economy and authorities.
The city is divided into ten districts. Each of them offers its own
charming atmosphere predicated upon its rich history. A good example can
be the Jewish Quarter (Josefov) known especially for the legend of Golem
and famous writer Franz Kafka. Then, walking the Parizska street (said to
be the most luxurious street in the city), there is the Old Town Square.
One of the most important squares of the city renowned for the rare Prague
Astronomical Clock (Orloj), number of galleries, Bethlehem Chapel and
a monument of religious reformer Jan Hus.
The next place of interest can be found in the area of the New Town. The
Wenceslas square with the monument of St. Wenceslas, the patron saint of
the Czech state, is the longest square of the republic. Its capacity is
fully used by various shops, restaurants, clubs and street artists. Also
the renaissance revival-styled building of National Museum, which is now
under reconstruction, is situated on the upper end of the square.
Modern art and architecture together with technical mastery demonstration
are represented by the Zizkov Television Tower, the Dancing House (Fred and
Ginger Building) or the Stefanik's Observatory on the Petrin hill located
in the neighbourhood of the quarter Hradcany. Also Krizik's light fountain
or Industrial Palace in the area of the Holesovice Showground are worth
seeing.
However, the dominant feature of the skyline is still created by the Prague
Castle and the Gothic St. Vitus Cathedral spires. The Golden Lane heading
down to the Lesser Town shows the tiny and colorful medieval houses. There
are many bridges connecting the banks of the Vltava River.
However, only one of them is well known in the whole world--the Charles
bridge. Czech King and Holy Roman Emperor Charles IV promoted its
construction in the 14th century. The bridge is 520 metres long and stands
for a connection between the Lesser Town and the Old Town. It was built in
the Gothic style as well as the St. Vitus Cathedral.
Charles IV was also the founder of the University, which now proudly bears
his name--The Charles University. It is one the world's oldest universities
and with 17 faculties, 3 institutes, 6 centres of teaching, research and
development it is also the largest and best rated university in the Czech
Republic. The students can choose some of the 642 courses within 300 of
accredited degree programmes in the field of medicine, law, theology,
pharmacy, arts, science, mathematics and physics, education, social
sciences, physical education and sports, and humanities.
We are justifiably very proud of the fact that the campus of the Charles
University is going to host the TSD2017 conference.
ABOUT CONFERENCE
The conference is organized by the Faculty of Applied Sciences, University
of West Bohemia, Pilsen, the Faculty of Informatics, Masaryk University,
Brno, and the Institute of Formal and Applied Linguistics, Faculty of
Mathematics and Physics of the Charles University.
The TSD2017 conference is officially recognized as an INTERSPEECH 2017
satellite event and it holds the status of an ISCA Supported Event as well.
Venue:
Faculty of Mathematics and Physics of the Charles University
Mala Strana Campus - "S" Building
Malostranske nam. 2/25
CZ-118 00 Praha 1
Accommodation:
Orea Hotel Pyramida ****
Belohorska 24
CZ-169 00 Praha 6
CONTACT
The preferred way of contacting the conference organizing committee is
writing an e-mail to:
Mrs Romana Strapkova, TSD2017 Conference Secretary
E-mail: tsd2017@tsdconference.org
Phone: (+420) 736 664 500
All paper correspondence regarding the conference should be addressed to:
TSD2017 - KIV
Fakulta aplikovanych ved
Zapadoceska univerzita v Plzni
Univerzitni 8
CZ-306 14 Plzen
Czech Republic
Fax: (+420) 377 632 402 -- Please, mark the faxed material with large
capitals 'TSD' on top.
TSD 2017 conference web site: http://www.tsdconference.org/tsd2017
------------------------------
Message: 3
Date: Thu, 26 Jan 2017 14:04:14 +0100
From: Artem Sokolov <gposhta@gmail.com>
Subject: [Moses-support] CFP: WMT 2017 *new* Shared Task on Bandit
Learning for Machine Tramslation
To: moses-support@mit.edu
Message-ID:
<CAAi4b7xQ7_Hp2OWJxcVP2U8rEYFQw5CRhHi18gACSGMbSwb6iw@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
CALL FOR PARTICIPATION
===============================================================
WMT 2017 Shared Task on Bandit Learning for Machine Translation
===============================================================
(collocated with EMNLP 2017)
Check the website for details:
http://www.statmt.org/wmt17/bandit-learning-task.html
###### BANDIT LEARNING FOR MACHINE TRANSLATION ######
Bandit Learning for MT is a framework to train and improve MT systems by
learning from weak or partial feedback: Instead of a gold-standard
human-generated translation, the learner only receives feedback to a single
proposed translation (this is why it is called partial), in form of a
translation quality judgement (which can be as weak as a binary
acceptance/rejection decision).
Amazon and University of Heidelberg organize this Shared Task with a goal to
encourage researchers to investigate algorithms for learning from weak user
feedback instead of from human references or post-edits that require skilled
translators. We are interested in finding systems that learn efficiently and
effectively from this type of feedback, i.e. they learn fast and achieve high
translation quality. Developing such algorithms is interesting for interactive
machine learning and for human feedback in NLP in general.
In the WMT task setup, the user feedback will be simulated by a service hosted
on Amazon Web Services (AWS), where participants can submit translations and
receive feedback and use this feedback for training an MT model. Reference
translations will not be revealed at any point, also evaluations are done via
the service.
###### IMPORTANT DATES ######
All dates are preliminary.
Registration via e-mail till March 19, 2017
Access to mock service March, 2017
Access to dev service March 28, 2017
Online learning starts April 25, 2017
Notification of results May 26, 2017
Paper submission deadline June 9, 2017
Acceptance notification June 30, 2017
Camera-ready deadline July 14, 2017
###### WHY IS IT CALLED BANDIT LEARNING? ######
The name bandit is inherited from a model where in each round a gambler in a
casino pulls an arm of a different slot machine, called "one-armed bandit",
with the goal of maximizing his reward relative to the maximal possible reward,
without apriori knowledge of the optimal slot machine. In MT, pulling an arm
corresponds to proposing a translation; rewards correspond to user feedback on
translation quality. Bandit learners can be seen as one-state Markov Decision
Processes (MDPs), which connects them to reinforcement learning. In MT,
proposing a translation corresponds to choosing an action.
###### ONLINE LEARNING PROTOCOL ######
Bandit learning follows an online learning protocol, where on each of a
sequence of iterations, the learner receives a source sentence, predicts a
translation, and receives a reward in form of a task loss evaluation of the
predicted translation. The learner does not know what the correct prediction
looks like, nor what would have happened if it had predicted differently.
FOR T = 1, ..., T DO
* RECEIVE SOURCE SENTENCE
* PREDICT TRANSLATION
* RECEIVE FEEDBACK TO PREDICTED TRANSLATION
* UPDATE SYSTEM
Online interaction is done via accessing an AWS-hosted service that provides
source sentences to the learner (step 1), and provides feedback (step 3) to the
translation predicted by the learner (step 2). The learner updates his
parameters using the feedback (step 4) and continues to the next example.
###### DATA ######
For training seed systems, out-of-domain parallel data shall be restricted to
German-English Europarl, NewsCommentary, CommonCrawl and Rapid data
for the WMT'17
News Translation (constrained) task, monolingual English data from the
constrained task is allowed.
The in-domain sequence of data for online learning will be e-commerce domain
provided by Amazon. These data can only be accessed via the service. No
reference translations will be revealed, only feedback to submitted
translations is returned from the service.
Simulated _reward-type_ real-valued feedback will be based on a combination of
several quality models, including automatic measures w.r.t. human references,
and will be normalized to the range [0,1] ('very bad' to 'excellent'). Feedback
can only be accessed via the service. Only one feedback is allowed per source
sentence.
###### SERVICES ######
Three AWS-hosted services will be provided:
* MOCK SERVICE to test client API: Will sample from a tiny dataset
and simply return BLEU as feedback.
* DEVELOPMENT SERVICE to tune algorithms and hyperparameters: Will
sample from a larger in-domain dataset. Feedback will be parameterized
differently from the learning service to prevent learning from
development data. Several runs will be allowed and evaluation results
will be communicated to the participants.
* ONLINE LEARNING SERVICE: Will sample from a very large in-domain
dataset. Participants will have to consume a fixed number of samples
during the allocated online learning period to be eligible for final
evaluation.
The respective data samples will be the same for all participants.
###### EVALUATION ######
The following main evaluation metrics will be used:
* ONLINE: cumulative per-sentence reward against the number of iterations,
* OFFLINE: standard automatic MT evaluation metric on a held-out
in-domain test set,
* RELATIVE to the out-of-domain starting point by doing test set
evaluations in the beginning and in the end of the online learning
sequence.
Note that all evaluations are done during online learning and not in a separate
offline testing phase.
###### HOW TO PARTICIPATE ######
* Pick your favourite MT system.
* Train an out-of-domain model on allowed data.
* REGISTER for the task via email (bandit_wmt@cl.uni-heidelberg.de)
and receive further instructions on how to access the service.
* Wrap CLIENT CODE SNIPPETS around your MT system.
* SETUP: Test the in-domain-training procedure with the MOCK SERVICE
and ensure that your client sends translations and receives feedback.
* TUNE: Find a clever strategy and good hyperparameters to learn from
weak feedback (e.g. by simulating weak feedback from parallel data, or
by using the DEVELOPMENT SERVICE).
* TRAIN your in-domain model by starting from your out-of-domain
model, submitting translations to the ONLINE LEARNING SERVICE,
receiving feedback and updating your model from this feedback.
###### ORGANIZERS ######
Amazon Development Center Berlin and Heidelberg University
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 123, Issue 15
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 123, Issue 15"
Post a Comment