LINGUIST List 15.437
Tue Feb 3 2004
Calls: Computational Ling/Portugal; Phonology/France
Editor for this issue: Andrea Berez <andrealinguistlist.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
Roberto Basili, Beyond Named Entity Recognition Semantic Labelling for NLP Tasks
gabriel.bergounioux, 6th Annual Meeting French Network of Phonology
Message 1: Beyond Named Entity Recognition Semantic Labelling for NLP Tasks
Date: Mon, 02 Feb 2004 15:18:17 +0100
From: Roberto Basili <basiliinfo.uniroma2.it>
Subject: Beyond Named Entity Recognition Semantic Labelling for NLP Tasks
FINAL CALL FOR PAPERS
Workshop
Beyond Named Entity Recognition Semantic Labelling for NLP Tasks
URL: http://ai-nlp.info.uniroma2.it/ws_lrec04/
Centro Cultural de Belem
LISBON, Portugal
25th May 2004
In Association with
4th INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION
LREC2004
Main conference 26-27-28 May 2004
Motivation and Aims
Although it is generally assumed that improvements in language
processing will be made through the integration of linguistic
information and statistical techniques, the reality is that language
is very diverse and looking for specific patterns of words that repeat
enough to be statistically significant tends not to be a very fruitful
task: sequences longer than three words are not generally repeated
often enough to be statistically significant. At the same time, the
identification of named entities: Names, dates, places, organizations
etc., has proved to be a very useful preliminary task in many natural
language processing systems are interested in pursuing approaches
which extend this notion by identifying and labeling other semantic
information in a text, in such as way as to allow repeatable semantic
patterns to emerge. Our interest is in attacking the data sparseness
problem by exploring ways to collapse (semantically) related phrases
which are expressed by different word sequences.
As this seems closely related to previously proposed class-based
language models (see for example Brown et al. 90 in Computational
Linguistics), it is distinguished because the empirical notion of
classes used in the previous work (e.g. classes made up of
collocationally similar words) are replaced by semantically justified
sets.
Notice how Name Entity (NE) tagging and Word Sense Disambiguation
(WSD) represent, in terms of granularity and representational
complexity, two extremes of a single general problem: semantic
disambiguation. Semantic disambiguation serves thus the purpose of
improving the generalization power of statistical models. One of the
questions here is how to determine a suitable level of clustering (for
NE identification and for WSD) that would lead to high accuracy and to
performance improvement by obtained statistical models.
Reason of Interest
It is to be noticed that a set of independent research work focused
recently on the statistical treatment of semantic phenomena
(e.g. WordNet navigation as a stochastic process, as studied in Light
and Abney or in Ciaramita & Johnson) highly correlates with the
research program proposed above.
The workshop will represent a forum where experience from lexical
semantics and statistical learning will be presented and fruitful
discussion among researchers in both fields will be promoted. The
workshop is expected to attract researchers and practitioners from a
range of areas as well as developers of large scale semantic resources
who are interested in effective methods of semantic labeling.
Topics (to be addressed in the workshop include, but are not limited
to)
* Methods for lexical - semantic annotation of corpora
* Methods and Standards for lexical semantic representation of
dictionary information
* Lexico-semantic taxonomies
* Existing sources of classification: dictionaries, thesauri and
computerized ontologies
* Corpus-driven methods for semantic disambiguation
* Feature selection for semantic disambiguation
* Lexico-semantic tagging of very large corpora
* Algorithms and methods for disambiguation of semantic phenomena
* Statistical learning models and their applications to semantic
labeling
* Computational learning frameworks for Natural Language Learning
* Semi-supervised and unsupervised statistical semantic disambiguation
* Evaluation of semantic disambiguation
Workshop format
The workshop will be a half-day event with position statements from
invited speakers (half an hour each) with two hours for 4-6
presentations of scientific papers. Submissions are intended to
present works in progress and more completed works which fall within
the scope defined by the topics listed above. A final 1 hour open
discussion among all the workshop participants will be moderated by
the organizers. In order to stimulate an interesting general
discussion each member of the program committee will be invited to
submit a position statement of max. 1000 words.
Submission
Participants are invited to submit an extended abstract of max. 3500
words concerning one or more of the topics of interest. Each accepted
paper receives a slot of 25 minutes for presentation (15 minutes talk
and 10 minutes for discussion). Each submission should show: title;
author(s); affiliation(s); and contact author's e-mail address, postal
address, telephone and fax numbers. Submissions must be sent
electronically in PDF to the following address:
Roberto Basili
Dept. of Computer Science, Systems and Management
University of Roma Tor Vergata
e-mail: basiliinfo.uniroma2.it
Proceedings and Publications
Proceedings of the workshop will be printed by the LREC Local
Organising Committee. The
http://www.elsevier.com/locate/issn/0885-2308 Computer, Speech and
Language journal will dedicate to the workshop topics a Special Issue
on "Semantic tagging/labelling for NLP tasks". Relevant papers
submitted to the workshop will be selected to appear in that special
issue.
Important dates
Extended abstract submission (max. 3500 words): 16th of February 2004
Notification of acceptance: 8th of March 2004
Preliminary Program: 29th of March 2004
Submission of the final version of paper: 5th of April 2004
Workshop: 25th May 2004
Organising Committee
Louise Guthrie - University of Sheffield, UK
Roberto Basili - University of Rome, Tor Vergata, Italy
Eva Hajicova - Charles University, Czech Republic
Frederick Jelinek - Johns Hopkins University, Maryland, USA
Further Information
For any information related to the organization, please contact:
Roberto Basili
e-mail: basiliinfo.uniroma2.it
Dept. of Computer Science, Systems and Management
University of Roma Tor Vergata
Via di Tor Vergata
00133 Roma (ITALY)
tel: +39 06 72597391
fax: +39 06 72597460
Message 2: 6th Annual Meeting French Network of Phonology
Date: Mon, 2 Feb 2004 16:42:32 -0500 (EST)
From: gabriel.bergounioux <gabriel.bergouniouxwanadoo.fr>
Subject: 6th Annual Meeting French Network of Phonology
6th Annual Meeting French Network of Phonology
Date: 03-Jun-2004 - 05-Jun-2004
Location: Orleans, France
Contact: Bergounioux Gabriel
Contact Email: gabriel.bergouniouxwanadoo.fr
Meeting URL: http://univ-orleans.fr
Linguistic Sub-field: Phonology
Call Deadline: 08-Apr-2004
Meeting Description:
6th Annual Meeting French Network of Phonology
Université d'Orléans
Thursday 3rd - Saturday 5th June 2004
Fax : *2 38 49 47 12
e-mail : institut.lettresuniv-orleans.fr
Abstracts are welcome on any area of phonological/phonetic
inquiry. Main topics : form and substance, constraints and
representations, primitives, diachrony, including sociolinguistic
approaches, generative approaches (OT, Lexical Phonology, Government
Phonology and others), acquisition studies, history and epistemology
of phonetics/phonology.
Abstracts should be two A4 pages (author's name and details on
separate sheet, please) and should be submitted by email to both
G. Bergounioux (gabriel.bergouniouxwanadoo.fr) and
(institut.lettresuniv-orleans.fr), ''Colloque phonologie''.
Language of abstracts and papers : French or English.
Deadline for abstracts: 08/04/04
Notification to authors : Before May, the 15th.
6e Journée Internationales du Réseau Français de Phonologie
(ex GDR 1954 Phonologie)
6th Annual Meeting French Network of Phonology
Université d'Orléans
Faculté des Lettres, Langues et Sciences Humaines
Domaine de la Source
10 rue de Tours. 45072 Orléans Cedex 02
3 - 5 juin 2004
Thursday 3rd - Saturday 5th June 2004
Soutiens financiers
CNRS (Réseau français de phonologie) - Université d'Orléans -
CORAL
Contact secrétariat :
Madame Bombereau 02 38 49 47 04
(tlj 8h30 - 12h15 / 13h30-17h sauf vendredi après-midi)
Fax : 02 38 49 47 12
e-mail : institut.lettresuniv-orleans.fr
courrier : Colloque Phonologie / Institut des Lettres
UFR LLSH / Université d'Orléans
10 rue de Tours
F-45072 Orléans Cedex 02
Inscription :
Les inscriptions se feront sur place avant l'ouverture du colloque
* étudiants : 15 euros
* non étudiants : 30 euros
* soirée-repas : 15 euros
Comité d'organisation local :
L. Abouda, O. Baude, G. Bergounioux, I. Eshkol, F. Nemo, J.-L. Rougé,
E. Schang.
Comité Scientifique/Scientific Committee:
Jean-Pierre Angoujard (Nantes), Gabriel Bergounioux (Orléans),
Joaquim Brandao de Carvalho (Paris 8), Nick Clements (ILPGA), Jacques
Durand (Toulouse II), Pierre Encrevé (EHESS), Bernard Laks (Paris X),
Jean Lowenstamm (Paris 7), Noël Nguyen (Aix), Tobias Scheer (Nice),
Nathalie Vallée (Grenoble III).
Time for papers : 30 minutes, plus 10 minutes for questions.
Please use SIL Doulos for phonetic symbols, and send your abstract as
a Word file.
We plan to run a poster session, if there are sufficient number of
poster papers offered. Please indicate whether you are prepared, or
would prefer, to offer your paper as a poster.
Deadline for abstracts: 08-Apr-2004
Notification to authors : Before May, the 15th.