CVSC 2014 - Workshop on Continuous Vector Space Models and their Compositionality

Workshop on Continuous Vector Space Models and their Compositionality (2nd edition)
Co-located with EACL 2014, Gothenburg, Sweden
April 27, 2014
Submission deadline: January 23, 2014
https://sites.google.com/site/cvscworkshop2014
First Call for Papers
(Apologies for multiple postings)
In recent years, there has been a growing interest in algorithms that learn and use continuous representations for words, phrases, or documents in many natural language processing applications. Among many others, influential proposals that illustrate this trend include latent Dirichlet allocation, neural network based language models and spectral methods. These approaches are motivated by improving the generalization power of the discrete standard models, by dealing with the data sparsity issue and by efficiently handling a wide context. Despite the success of single word vector space models, they are limited since they do not capture compositionality. This prevents them from gaining a deeper understanding of the semantics of longer phrases or sentences.
With the growing popularity of these neural and probabilistic methods of language processing, the scope of this second workshop is extended to theoretical and conceptual questions regarding:
* their relation to unsupervised distributional representations,
* the encompassing of the compositional aspects of formal models of semantics,
* the role of linguistic theory in the design and development of these methods.
Some such pertinent questions include: Should phrase representations and word representations be of the same sort? Could different linguistic levels require different modelling approaches? Is compositionality determined by syntax, and if so, how do we learn/define it? Should word representations be fixed and obtained distributionally, or should the encoding be variable? Should word representations be task-specific, or should they be general?
In this workshop, we invite submissions of papers on continuous vector space models for natural language processing. Topics of interest include, but are not limited to:
* learning algorithms for continuous vector space models,
* their compositionality,
* their use in NLP applications,
* spectral learning for NLP,
* neural networks for NLP,
* phrase, sentence, and document-level distributional representations,
* tensor models,
* distributed semantic representations,
* the role of syntax in compositional models,
* formal and distributional semantic models.
INVITED SPEAKERS
The workshop will showcase presentations from two invited speakers : Geoffrey Zweig (Microsoft Research) and a second presenter to be announced soon.
SUBMISSION INFORMATION
Authors should submit a full paper of up to 8 pages in electronic, PDF format, with up to 2 additional pages for references. The reported research should be substantially original. The papers will be presented orally or as posters. All submissions must be in PDF format and must follow the EACL 2014 formatting requirements (http://www.eacl2014.org/files/eacl-2014-styles.zip). Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well. Submissions must be made through the Softconf website set up for this workshop:
https://www.softconf.com/eacl2014/CVSC/
Accepted papers will appear in the workshop proceedings, where no distinction will be made between papers presented orally or as posters.
IMPORTANT DATES
23 January 2014 : Submission deadline
20 February 2014 : Notification of acceptance
3 March 2014 : Camera-ready deadline
27 April 2014 : Workshop
ORGANIZERS
Alexandre Allauzen (LIMSI-CNRS/Université Paris-Sud, France)
Raffaella Bernardi (University of Trento, Italy)
Edward Grefenstette (University of Oxford, UK)
Hugo Larochelle (Université de de Sherbrooke, Canada)
Christopher Manning (Stanford University, USA)
Scott Wen-tau Yih (Microsoft Research, USA)
PROGRAM COMMITTEE
Nicholas Asher (IRIT-Toulouse)
Marco Baroni (University of Trento)
Yoshua Bengio (Université de Montréal)
Gemma Boleda (University of Texas)
Antoine Bordes (Université Technologique de Compiègne)
Johan Bos (University of Groningen)
Léon Bottou (Microsoft Research)
Xavier Carreras (Universitat Politècnica de Catalunya)
Lucas Champollion (New-York University)
Stephen Clark (University of Cambridge)
Shay Cohen (Columbia University)
Ido Dagan (Bar Ilan University)
Ronan Collobert (IDIAP Research Institute, Switzerland)
Pino Di Fabbrizio (Amazon)
Georgiana Dinu (University of Trento)
Kevin Duh (Nara Institute of Science and Technology)
Dean Foster (University of Pennsylvania)
Alessandro Lenci (University of Pisa)
Louise McNally (Universitat Pompeu Fabra)
Fabio Massimo Zanzotto (Università degli Studi di Roma)
Mirella Lapata (University of Edinburgh)
Andriy Mnih (Gatsby Computational Neuroscience Unit)
Larry Moss (Indiana University)
Diarmuid Ó Seaghdha (University of Cambridge)
Sebastian Pado (Universität Stuttgart)
Martha Palmer (University of Colorado)
John Platt (Microsoft Research)
Maarten de Rijke (University of Amsterdam)
Mehrnoosh Sadrzadeh (University of London)
Mark Steedman (University of Edinburgh)
Chung-chieh Shan (Indiana University)
Peter Turney (NRC)
Jason Weston (Google)
Guillaume Wisniewski (LIMSI-CNRS/Université Paris-Sud)