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
esslli:start [2007/11/27 21:55]
alexlenci 		esslli:start [2010/11/01 14:07] (current)
Line 1: Line 1:
-Draft of the Expression of Interest Call: +The page you are looking for has moved to [[http://wordspace.collocations.de/doku.php/workshop:esslli:start]].
- +
- +
-Corpus-based distributional models (such as LSA or HAL) +
-have been claimed to capture interesting aspects of word meaning.  +
-Although they have been proposed as +
-plausible simulations of human semantic space organization, +
-careful and extensive empirical tests of such claim is still lacking. +
- +
-Evaluation of these models has tended to focus on large scale +
-quantitative tasks, often more oriented towards engineering +
-applications (see, e.g., the recent SEMEVAL evaluation campaign) than +
-towards the challenges from formal semantics, linguistic theory, +
-philosophy and cognitive science. This has resulted into a great divide  +
-between corpus-driven computational approaches to semantics and more +
-symbolic approaches, typical 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 (typically limited to semantic similarity detection), +
- 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 single scholars +
-and research teams 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. Specifically, we envisage the +
-following tasks: +
- +
-- categorization; +
-  * concrete nouns categorization; +
-  * concrete vs. abstract nouns discrimination; +
-  * verbs categorization; +
- +
-- MISSING TASK +
- +
- +
-- property generation; +
- +
- +
-- MISSING TASK +
- +
- +
-The focus is NOT on competition, but on understanding how different +
-models highlight different semantic aspects, and how far we are from +
-integrated models of all such aspects. In fact, we believe that the current +
-state of the art on computational semantics  +
-does not need to discover the best model, but rather +
-to enlarge the understanding of the limits and potentialities  +
-of different approaches when confronted with cognitively realistic tasks.  +
-To this effect, annotated +
-datasets will be distributed to the participants, that will be +
-encouraged to explore them and highlight interesting aspects of their +
-models' performance, perform quantitative and qualitative error analysis, etc. +
- +
-Theoretical and experimental papers related to the task datasets and +
-simulation results are also invited. +
- +
-Through collaborative preparatory work on the Word Space wiki +
-(http://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 applicative +
-point of view. +
- +
-We ask for expressions of interest from researchers and teams that +
-might take part in the initiative and might want to have a say in test +
-set design (a subsequent mail will provide deadlines for data-set +
-creation and workshop submission.) +
- +
-XXX CONTACT INFO XXX+
  
 +[[:workshop:esslli:start|Click here]] to go to the page.

You are here: start » esslli