LINGUIST List 18.2767
|
Mon Sep 24 2007
Calls: Computational Ling/Spain; Computational Ling/Morocco
Editor for this issue: Ania Kubisz
<ania linguistlist.org>
|
As a matter of policy, LINGUIST discourages the use of abbreviations
or acronyms in conference announcements unless they are explained in
the text. To post to LINGUIST, use our convenient web form at
http://linguistlist.org/LL/posttolinguist.html.
|
Directory
1. Kutz
Arrieta,
Mixing Approaches to Machine Translation
2. Helene
Mazo,
Language Resources and Evaluation Conference
Message 1: Mixing Approaches to Machine Translation
|
Date: 20-Sep-2007
From: Kutz Arrieta <karrietavicomtech.org>
Subject: Mixing Approaches to Machine Translation
 E-mail this message to a friend
Full Title: Mixing Approaches to Machine Translation
Date: 14-Feb-2008 - 14-Feb-2008
Location: Donostia, Basque Country, Spain
Contact Person: Kepa Sarasola
Meeting Email: ksarasolasi.ehu.es
Linguistic Field(s): Computational Linguistics
Call Deadline: 26-Nov-2007
Meeting Description
Workshop: 'Mixing Approaches to Machine Translation'
Thursday February 14th 2008, Donostia - San Sebastián. Basque Country
First Call for Papers
Workshop: ''Mixing Approaches to Machine Translation''
Thursday February 14th 2008, Donostia - San Sebastián. Basque Country
http://ixa2.si.ehu.es/matmt-2008
Background
The aim of the workshop ''Mixing Approaches To Machine Translation'' is to
promote practical hybrid approaches to MT, combining resources and
algorithms coming from rule-based, example-based or statistical approaches.
The boundaries between the three principal approaches to MT (rule-based,
example-based, statistical) are becoming narrower:
(i) Phrase based SMT models are incorporating morphology, syntax and
semantics into their systems.
(ii) Rule based systems are using parallel corpora to enrich their lexicons
and grammars, and to create new methods for disambiguation.
(iii) Previous ASR/ALT projects have shown that in a MT system benefits can
be realized by a simple combination of different MT approaches in a Rover
architecture.
Data-driven Machine Translation (example-based or statistical) is nowadays
the most prevalent trend in Machine Translation research.
Translation results obtained with this approach have now reached a high
level of accuracy, especially when the target language is English. But
these Data-driven MT systems base their knowledge on aligned bilingual
corpora, and the accuracy of their output depends heavily on the quality
and the size of these corpora. Large and reliable bilingual corpora are
unavailable for many language pairs.
Workshop Programme
Structure:
1. Invited talks
2. Programme papers
3. Panel discussion
Keynote speakers:
- Koehn, Philipp (University of Edinburgh, UK)
- Ney, Hermann (Rheinisch-Westfälische Technische Hochschule, Germany)
- Way, Andy (Dublin City University, Ireland)
Workshop topics
We are particulartly interested in papers describing research and
development in the following areas:
- Comparing different approaches for developing MT
- Methods to compare and integrate translation outputs obtained with
different MT approaches.
- MT evaluation methods, especially those suitable for languages with rich
morphology.
- Morphology-, syntax- or semantic-augmented SMT models
- Research developed using OpenSource language resources for developing
hybrid MT
Paper submission
Papers should be written in English and no longer than 8 pages.
Use the same file template as was used for the TMI-07 conference.
http://www.computing.dcu.ie/~away/TMI-07/guidelines.html
Papers should be sent via e-mail to i.alegriaehu.es All contributions will
be published in the workshop proceedings.
Important Dates
- Paper submission deadline: Nov 26, 2007
- Notification of acceptance: Jan 9, 2007
- Camera-ready papers: Jan 20, 2007
- Workshop: Feb 14, 2008
Programme Committee
- Iñaki Alegria (University of the Basque Country, Donostia)
- Kutz Arrieta (Vicomtech, Donostia)
- Núria Castell (Technical University of Catalonia, TALP, Barcelona)
- Arantza Diaz de Ilarraza (University of the Basque Country, Donostia)
- David Farwell (Technical University of Catalonia, TALP, Barcelona)
- Mikel Forcada (University of Alacant, Alicante)
- Philipp Koehn (University Of Edinburgh, UK)
- Lluis Marquez (Technical Univ. of Catalonia, Barcelona)(Co-chair)
- Hermann Ney (Rheinisch-Westfälische Technische Hochschule, Aachen)
- Kepa Sarasola (University of the Basque Country, Donostia) (Co-chair)
Local organizers
IXA Group, University of the Basque Country
Alegria I., Casillas A., Díaz de Ilarraza A., Igartua J., Labaka G.,
Lersundi M., and Sarasola K.
Elhuyar Fundazioa
Gurrutxaga A., Leturia,I., and Saralegi X.
About the OpenMT project
The main goal of the OpenMT project is the development of an Open Source
Machine Translation Architecture based on hybrid models and advanced
semantic processors. These architectures will be Open Source systems
combining the three main Machine Translation frameworks - Rule-Based MT,
Statistical MT, and Example-Based MT -- into hybrid systems. Defined
architectures and results of the project will be Open Source, this will
allow a fast development and adaptation of new advanced Machine Translation
systems for other languages. We will test the functionality of this system
with different languages: English, Spanish, Catalan and Basque. Corpora are
easily available for English and Spanish, but not so for the remaining
languages. While the structure of some of those languages is very similar
(Catalan and Spanish), others are very different (English and Basque).
Basque is an agglutinative language with a very rich morphology, unlike
English, Catalan and Spanish.
The highlights of the OpenMT project are:
- The design of hybrid systems combining traditional linguistic rules,
example-based methods and statistical methods.
- That it is an Open Source Initiative
- The use of advanced syntactic and semantic processing
http://ixa.si.ehu.es/openmt
Message 2: Language Resources and Evaluation Conference
|
Date: 17-Sep-2007
From: Helene Mazo <lreclrec-conf.org>
Subject: Language Resources and Evaluation Conference
E-mail this message to a friend
Full Title: Language Resources and Evaluation Conference
Short Title: LREC
Date: 26-May-2008 - 01-Jun-2008
Location: Marrakech, Morocco
Contact Person: Helene Mazo
Meeting Email: lreclrec-conf.org
Web Site: http://www.lrec-conf.org/lrec2008/
Linguistic Field(s): Computational Linguistics
Call Deadline: 31-Oct-2007
Meeting Description
LREC 2008 - 6th Language Resources and Evaluation Conference
Main Conference: 28-30 May 2008
Workshops and Tutorials: 26-27 May and 31 May - 1 June 2008
The sixth international conference on Language Resources and Evaluation (LREC)
will be organised in 2008 by ELRA in cooperation with a wide range of
international associations and organisations.
Palais des Congrès Mansour Eddahbi, Marrakech - Morocco
Conference web site: http://www.lrec-conf.org/lrec2008/
LREC 2008 - 6th Language Resources and Evaluation Conference
Second Call for Papers
Palais des Congrès Mansour Eddahbi, Marrakech - Morocco
Conference web site: http://www.lrec-conf.org/lrec2008/
The sixth international conference on Language Resources and Evaluation (LREC)
will be organised in 2008 by ELRA in cooperation with a wide range of
international associations and organisations, including AAMT, AMTA, ACL, ALTA,
COCOSDA and Oriental COCOSDA, EACL, EAMT, ELSNET, EURALEX, GWA, IAMT,
KnowledgeWeb, LDC, NEMLAR Network, SIGLEX, TEI, Technolangue French Program,
WRITE and with major national and international organisations including the
European Commission - Information Society and Media, Unit E.2 ''Content and
Knowledge''.
Conference Aims
In 10 years - the first LREC was held in Granada in 1998 - LREC has become the
major event on Language Resources (LRs) and Evaluation for Human Language
Technologies (HLT). The aim of LREC is to provide an overview of the
state-of-the-art, explore new R&D directions and emerging trends, exchange
information regarding LRs and their applications, evaluation methodologies and
tools, ongoing and planned activities, industrial uses and needs, requirements
coming from the e-society, both with respect to policy issues and to
technological and organisational ones.
LREC provides a unique forum for researchers, industrials and funding agencies
from across a wide spectrum of areas to discuss problems and opportunities, find
new synergies and promote initiatives for international cooperation, in support
to investigations in language sciences, progress in language technologies and
development of corresponding products, services and applications, and standards.
Conference Topics
Issues in the design, construction and use of Language Resources (LRs): text,
speech, multimodality
- Guidelines, standards, specifications, models and best practices for LRs
- Methodologies and tools for LRs construction and annotation
- Methodologies and tools for the extraction and acquisition of knowledge
- Ontologies and knowledge representation
- Terminology
- Integration between (multilingual) LRs, ontologies and Semantic Web technologies
- Metadata descriptions of LRs and metadata for semantic/content markup
Exploitation of LRs in different types of systems and applications
- For: information extraction, information retrieval, speech dictation, mobile
communication, machine translation, summarisation, web services, semantic
search, text mining, inferencing, reasoning, etc.
- In different types of interfaces: (speech-based) dialogue systems, natural
language and multimodal/multisensorial interactions, voice activated services, etc.
- Communication with neighbouring fields of applications, e.g. e-government,
e-culture, e-health, e-participation, mobile applications, etc.
- Industrial LRs requirements, user needs
Issues in Human Language Technologies evaluation
- HLT Evaluation methodologies, protocols and measures
- Validation, quality assurance, evaluation of LRs
- Benchmarking of systems and products
- Usability evaluation of HLT-based user interfaces, interactions and dialogue
systems
- Usability and user satisfaction evaluation
General issues regarding LRs & Evaluation
- National and international activities and projects
- Priorities, perspectives, strategies in national and international policies
for LRs
- Open architectures
- Organisational, economical and legal issues
Special Highlights
LREC targets the integration of different types of LRs - spoken, written, and
other modalities - and of the respective communities. To this end, LREC
encourages submissions covering issues which are common to different types of
LRs and language technologies.
LRs are currently developed and deployed in a much wider range of applications
and domains. LREC 2008 recognises the need to encompass all those data that
interact with language resources in an attempt to model more complex human
processes and develop more complex systems, and encourages submissions on topics
such as:
- Multimodal and multimedia systems, for Human-Machine interfaces, Human-Human
interactions, and content processing
- Resources for modelling language-related cognitive processes, including emotions
- Interaction/Association of language and perception data, also for robotic systems
Programme
The Scientific Programme will include invited talks, oral presentations, poster
and demo presentations, and panels.
There is no difference in quality between oral and poster presentations. Only
the appropriateness of the type of communication (more or less interactive) to
the content of the paper will be considered.
Abstract Submission
On-line submission form for abstracts is now available: please go to the
''Abstract submission'' section on the LREC2008 web site
(http://www.lrec-conf.org/lrec2008) and follow the procedure instructions.
Submitted abstracts of papers for oral and poster or demo presentations must
consist of about 1500-2000 words.
Workshop, Tutorials and Panels
Submission of workshop, tutorial and panel proposals should be made by e-mail to
the following e-mail address: lreclrec-conf.org and will be reviewed by the
Programme Committee.
Proposals for workshops and tutorials should be no longer than three pages, and
include:
For workshops
The title
A brief technical description of the specific technical issues that the workshop
will address
The reasons why the workshop is of interest
The names and affiliations, postal addresses, phone and fax numbers, email and
web site addresses of the organising committee, which should consist of at least
three people knowledgeable in the field, coming from different institutions
The name and the e-mail address of the member of the workshop organising
committee designated as the contact person
The desirable duration of the workshop (half day or full day)
A summary of the intended call for participation
An estimate of the approximate audience size
A list of audio-visual or technical requirements and any special room requirements
The workshop proposers will be responsible for the organisational aspects (e.g.
workshop call preparation and distribution, review of papers, notification of
acceptance, assembling of the workshop proceedings using the ELRA
specifications, etc.).
For tutorials
The title
A brief technical description of the tutorial content
The reasons why the tutorial is of interest
The names and affiliations, postal addresses, phone and fax numbers, email and
web site addresses of the tutorial speakers, with brief descriptions of their
technical background
The name and e-mail address of one tutorial speaker designated as the contact person
The duration of the tutorial (half day is the expected usual length)
An estimate of the approximate audience size
A list of audio-visual or technical requirements and any special room requirements
The tutorial proposers will be responsible for the organisational aspects (e.g.
assembling of the tutorial material, etc.).
Proposals for panels should contain the following information:
The title
A brief technical description of the specific technical issues that the panel
will address
The reasons why the panel is of interest
Name of the panel organiser/s; affiliation and postal address; phone and fax
numbers; e-mail address; web site address
The name and the e-mail address of the designated contact person
Important Dates
Submission of proposals for panels, workshops and tutorials: 31 October 2007
Submission of proposals for oral and poster/demo papers: 31 October 2007
Notification of acceptance of panels, workshops and tutorials proposals: 22
November 2007
Notification of acceptance of oral papers, posters: 4 February 2008
Final version of papers for the proceedings: 25 March 2008
Conference: 28-30 May 2008
Pre-conference workshops and tutorials: 26 and 27 May 2008
Post-conference workshops and tutorials: 31 May and 1 June 2008
Consortia and Project Meetings
Consortia or projects wishing to take this opportunity for organising meetings
should contact well in advance the organisers at the following e-mail address:
lreclrec-conf.org.
Proceedings
The Proceedings on CD will include both oral and poster papers, in the same
format. In addition a Book of Abstracts will be printed.
Conference Programme Committee
Nicoletta Calzolari, Istituto di Linguistica Computazionale del CNR, Pisa ,
Italy (Conference chair)
Khalid Choukri, ELRA, Paris, France
Bente Maegaard, CST, University of Copenhagen, Denmark
Joseph Mariani, LIMSI-CNRS, Orsay, France
Jan Odijk, Nuance Communications International, Belgium and UIL-OTS, Utrecht,
The Netherlands
Stelios Piperidis, Institute for Language and Speech Processing (ILSP), Athens,
Greece
Daniel Tapias, Telefónica Móviles España, Madrid, Spain
The composition of the committees as well as instructions and addresses for
registration and accommodation in Marrakech will be detailed on the conference
website at http://www.lrec-conf.org/lrec2008/.
Read more issues|LINGUIST home page|Top of issue
|
|
Please report any bad links or misclassified data
LINGUIST Homepage | Read
LINGUIST | Contact us
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.
|
|
