Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Next revision Both sides next revision
esslli:start [2008/06/18 15:45]
schtepf 		esslli:start [2008/08/13 17:03]
schtepf
Line 2: Line 2:
  
 **Bridging the gap between semantic theory and computational simulations**\\ **Bridging the gap between semantic theory and computational simulations**\\
-//Workshop at [[http://www.illc.uva.nl/ESSLLI2008/|ESSLLI 2008]], Hamburg, August 4-9 2008// +//Workshop at [[http://www.illc.uva.nl/ESSLLI2008/|ESSLLI 2008]], Hamburg, August 4-8 2008// 
  
 +  * [[esslli:background|Background and motivation]]
 +  * [[esslli:proceedings|Workshop programme and proceedings]]
 +  * [[esslli:task|Shared tasks]]
 +  * [[esslli:cfp|Call for papers]]
  
 +===== Invited speakers =====
  
 +  * //Generating Semantic Representations From Simple Word Co-occurrence Statistics//\\ John A. Bullinaria (Birmingham)
 +  * //Distributional and Compositional Semantics//\\ Peter Bosch (Osnabrück)
  
-===== Background and motivation ===== 
  
-[[http://wordspace.collocations.de/lib/exe/fetch.php/esslli:lexical_semantics_workshop_-_motivational_poster.pdf?id=esslli%3Astart&cache=cache|{{ esslli:motivational_poster_thumb.jpg|Motivational Poster}}]] +===== Programme Committee =====
- +
-Corpus-based distributional models (such as LSA or HAL) +
-have been claimed to capture interesting aspects of word meaning +
-and provide an explanation for the rapid acquisition of semantic +
-knowledge by human language learners.  +
-However, although these models have been proposed as +
-plausible simulations of human semantic space organization, +
-careful and extensive empirical tests of such claims are still lacking. +
- +
-Systematic evaluations typically focus on large-scale +
-quantitative tasks, often more oriented towards engineering +
-applications (see, e.g., the recent SEMEVAL evaluation campaign) than +
-towards the challenges posed by linguistic theory, +
-philosophy and cognitive science.  This has resulted in a great divide  +
-between corpus-driven computational approaches to semantics on the one +
-hand and theory-driven symbolic approaches on the other -- a situation that +
-is characteristic of the linguistic and of most +
-of the cognitive tradition. +
-Moreover, whereas human lexical semantic competence is obviously +
-multi-faceted -- ranging from free association to taxonomic judgments to +
-relational effects -- tests of distributional models tend to focus on a +
-single aspect (most typically the detection of semantic similarity), +
-and few if any models have been tuned to tackle +
-different facets of semantics in an integrated manner. +
- +
-Our workshop purports to fill these gaps by inviting research teams and +
-individual scholars to test their computational models on a variety of small but +
-carefully designed tasks that aim to bring out linguistically and +
-cognitively interesting aspects of semantics +
-([[#Tasks and data sets|see below]] for details).  To this effect, annotated +
-datasets are available to the participants, who are +
-encouraged to explore them and highlight interesting aspects of their +
-models' performance, conduct quantitative and qualitative error analysis, etc. +
- +
-The focus is NOT on competition, but on understanding how different +
-models highlight different semantic aspects, how far we are from +
-an integrated model, and which aspects of semantics are beyond the +
-reach of purely distributional approaches.  +
-In fact, we believe that at the current state of the art in +
-computational and distributional semantics, our goal should not be +
-to develop the best-performing model for a specific application, but rather +
-to enlarge our understanding of the limits and potentialities  +
-of different approaches when confronted with cognitively realistic tasks.  +
- +
-In addition to these practical tasks, theoretical and experimental papers +
-discussing the relation between distributional and symbolic approaches to meaning +
-are also invited.  We are particularly interested in papers that analyze our +
-task data sets from a theoretical perspective or that discuss simulation results +
-and their implications for semantic and cognitive theory. +
- +
-Through collaborative preparatory work on the Word Space wiki ([[http://wordspace.collocations.de/|wordspace.collocations.de]]) and thanks to the ESSLLI multiple-day workshop format, we hope that this initiative will foster +
-collaboration among the nascent community of researchers interested in computational semantics from a theoretical rather than engineering-oriented point of view. +
- +
-For further information, please write to [[lexsem08@gmail.com|lexsem08@gmail.com]], and/or subscribe to the [[http://wordspace.collocations.de/doku.php/wiki_subscription|workshop wiki RSS feed]]. +
- +
- +
- +
- +
- +
- +
- +
-===== Tasks and data sets ===== +
- +
-In order to reach a better understanding of the possibilities and limitations +
-of distributional models of word meaning, we envisaged a number of tasks that +
-focus on linguistic and cognitive challenges rather than application engineering. +
- +
-Small annotated data sets are available on the workshop page and participants are invited +
-to apply their computational models and conduct a thorough analysis of the results. +
-The goal is not to achieve better precision than competitors, but to understand +
-the strengths and weaknesses of individual models, analyze and explain errors, etc. +
-Theoretical discussions of the data sets from a linguistic or cognitive perspective +
-are also invited and will complement the empirical findings. +
- +
-Ongoing work on data set preparation can be monitored at [[http://wordspace.collocations.de/doku.php/data:start|http://wordspace.collocations.de/doku.php/data:start]].  +
- +
-We offer the following tasks (click on the links for detailed task descriptions and downloads): +
- +
-  * **categorization** +
-    * [[data:Concrete Nouns Categorization|concrete nouns categorization]] +
-    * [[data:Abstract/Concrete Nouns Discrimination|abstract/concrete nouns discrimination]] +
-    * [[data:Verb Categorization|verb categorization]] +
-  * **modelling free association** +
-    * [[data:Correlation with Free Association Norms|correlation with free association norms]] +
-  * **generation of salient properties of concepts** +
-    * [[data:Comparison with Speaker-Generated Features|comparison with speaker-generated features]] +
- +
- +
-===== Workshop information ===== +
- +
-=== Dates === +
- +
-  * **April 4, 2008**: Paper submission deadline +
-  * **April 24, 2008**: Notification +
-  * **August 4-9, 2008**: Workshop in Hamburg (during the first week of ESSLLI) +
- +
- +
-=== Programme Committee ===+
  
 Marco Baroni (University of Trento) **(co-organizer)**\\ Marco Baroni (University of Trento) **(co-organizer)**\\
Line 140: Line 48:
  
  
- 
- 
- 
-===== Paper submission ===== 
- 
-We welcome papers reporting results of experimenting 
-with word space models on one or more workshop tasks, as well as 
- comparing different models on the same task(s) (authors are asked to carry out their own evaluation, using, if possible, the tools provided on the Website). 
- 
-We also welcome papers focussing on: 
-  * methodological and theoretical issues concerning word space models; 
-  * open challenges for distributional methods for semantic analysis; 
-  * interactions with formal approaches to meaning; 
-  * interaction with cognitive research on human semantic memory. 
- 
-The papers should not be longer than 8 pages, and they should be 
-submitted anonymously in PDF format following the 
-[[http://www.ling.ohio-state.edu/acl08/stylefiles.html|ACL 2008 stylesheet]]. 
- 
-Submission must be sent to [[lexsem08@gmail.com|lexsem08@gmail.com]], 
-no later than **April 4**, 
-specifying PAPER SUBMISSION in the subject and the authors' 
-names and affiliation in the message body. 
- 
- 
-=== Workshop homepage === 
-[[http://wordspace.collocations.de/doku.php?id=esslli:start|http://wordspace.collocations.de/doku.php?id=esslli:start]] 
- 
-=== ESSLLI 2008 homepage === 
-[[http://www.illc.uva.nl/ESSLLI2008/|http://www.illc.uva.nl/ESSLLI2008/]] 
  
  
  

You are here: start » esslli