Call
The hybrid approach term covers a large set of situations in which
different approaches are combined in order to better process textual
data and to attempt a better achievement of the dedicated task.
Among the hybridizations the possible combinations are unlimited. The
most frequent combination, as stressed during The Balancing Act in
1994, addressed machine learning and rule-based systems. Beyond this,
the hybridization can be augmented with distributionnal approaches,
syntactic and morphological analyses, semantic distances and
similarities, graph theory models, cooccurrences of linguistic units
(e.g., word and their dependencies, word senses and pos-tag, NEs and
semantic roles,...), knowledge-based approaches (terminologies and
ontologies), etc.
As a matter of fact, the hybridization implies to define a strategy to
efficiently combine several approaches: cooperation between
approaches, filtering, voting or ranking of the multiple system
outputs, etc.
Indeed, the combination of these different methods and approaches
appears to provide more complete and performant results. The reason is
that each method is sensitive and efficient with given data and within
given contexts. Hence, their combination may improve both precision
and recall. The coverage is indeed improved, while the exploitation of
different methods may also lead to the improvement of the precision
since their use within filtering, voting etc. modes becomes possible.
In this workshop, we favour the extended meaning of the hybridization
of methods, applied to various application areas, such as (but do not
feel constrained by these):
- automatic creation of linguistic resources
- POS tagging
- building and structuring of terminologies
- information retrieval and filtering
- information extraction
- linguistic annotation
- semantic labeling
- sign language recognition and transcription
- oral data transcription
- filtering and validation of lexical resources
- text summarization
- question/answering system
- natural language generation
- etc.
We invite authors to submit novel methods and novel conceptions of the
hybridization performed in various areas related to the textual data
processing.
Program Committee
- Anders Ardö, EIT, LTH, Lund University, Sweden
- Delphine Bernhard, LiLPa, Université de Strasbourg, France
- Wray Duntine, NICTA, Australia
- Philipp Cimiano, CITEC, University of Bielefeld, Germany
- Vincent Claveau, IRISA-CNRS, Rennes, France
- Kevin Cohen, University of Colorado Health Sciences Center, USA
- Marie-Claude l'Homme, OLST, Université de Montreal, Canada
- Béatrice Daille, Université de Nantes, LINA, France
- Stefan Th. Gries, University of California, Santa Barbara, USA
- Anna Kazantseva, University of Ottawa, Canada
- Mikaela Keller, CNRS LIFL UMR8022, Mostrare INRIA, Université Lille 1&3, France
- Alistair Kennedy, University of Ottawa, Canada
- Ben Leong, University of North Texas, USA
- Pierre Nugues, CS, LTH, Lund University, Sweden
- Bruno Pouliquen, WIPO, Geneva, Switzerland
- Sampo Pyysalo, National Centre for Text Mining, University of Manchester, United Kingdom
- Mathieu Roche, LIRMM, Université de Montpellier 2, France
- Patrick Ruch, Haute école de gestion de Genève, Switzerland
- Paul Thompson, National Centre for Text Mining, University of Manchester, United Kingdom
- Juan-Manuel Torres Moreno, LIA, Université d'Avignon et des Pays de Vaucluse, France
- Özlem Uzuner, University at Albany, State University of New York, USA
