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
course:start [2009/07/15 23:00]
schtepf 		course:start [2021/07/23 15:51] (current)
schtepf [Schedules & handouts]
Line 1: Line 1:
-====== Distributional Semantic Models (ESSLLI 2009)  ======+====== Courses and Tutorials on DSM  ======
  
-**Distributional Semantic Models: Theory and empirical results**\\ +These pages provide information, handouts and supplementary materials for courses and tutorials on Distributional Semantic Models, developed by [[http://clic.cimec.unitn.it/marco/|Marco Baroni]], [[http://purl.org/stefan.evert|Stefan Evert]] and [[http://www.humnet.unipi.it/linguistica/Docenti/Lenci/index.htm|Alessandro Lenci]].  If you would like to use our work for your own teaching, please send us an e-mail.
-//Advanced course at [[http://esslli2009.labri.fr/|ESSLLI 2009]], Bordeaux, July 27-31, 2009// +
  
-  * [[course:material|Downloads and Web interfaces]] +===== Schedules & handouts =====
-  * [[course:bibliography|Suggested reading (bibliography)]]+
  
-===== Course description =====+  * Advanced course on [[course:esslli2009:start|Distributional Semantic Models (ESSLLI '09)]] by Alessandro Lenci & Stefan Evert 
 +  * [[course:acl2010:start|DSM Tutorial (NAACL-HLT 2010)]] by Stefan Evert 
 +  * Introductory course on [[:course:esslli2018:start|Distributional Semantics (ESSLLI '16, '18)]] by Stefan Evert 
 +  * Foundational course on [[:course:esslli2021:start|Hands-on Distributional Semantics (ESSLLI '21)]] by Stefan Evert & Gabriella Lapesa
  
-Distributional semantic models (DSMs) are based on the assumption that the meaning of a word can (at least to a certain extent) be inferred from its usage, i.e. its distribution in text. Therefore, these models dynamically build semantic representations – in the form of multi-dimensional vector spaces – through a statistical analysis of the contexts in which words occur. +===== General information =====
-With their distributed vector-space representations, DSMs challenge traditional symbolic accounts of conceptual and semantic structures. However, their true ability to address key issues of lexical meaning is still poorly understood, and will have to be carefully evaluated in linguistic and cognitive research.+
  
-This course aims to equip participants with the necessary background knowledge for carrying out cutting-edge research in this area. In addition to teaching the mathematical foundations of DSMs and their applications in semantic analysis, we put particular emphasis on getting an intuitive grasp of the high-dimensional vector spaces, and on relating the computational models to fundamental issues of semantic theory.  The course is highly interdisciplinary and will be of interest to theoretical linguists, computational linguists and cognitive scientists alike.+  * [[course:material|Software & data sets]] 
 +  * [[course:bibliography|Bibliography & links]]
  
-**Lecturers:** [[http://purl.org/stefan.evert/|Stefan Evert]] (U Osnabrück), [[http://www.humnet.unipi.it/linguistica/Docenti/Lenci/index.htm|Alessandro Lenci]] (U Pisa) 
- 
-{{:icon_tip.png?32 }} 
-**Important note:**  
-Handouts and other materials for the course will be made available on this Web page and updated during the course.  Participants are therefore encouraged to bring a laptop computer so they can download and read the latest versions of our handouts. 
-We also plan to provide code examples for constructing and analyzing small-scale DSMs in [[http://www.r-project.org/|R]] (a powerful statistical computing environment and programming language), as well as some toy data sets.  If you wish to try these examples during the course, we recommend that you install R and the following add-on packages in advance: ''MASS'', ''Matrix'', ''e1071'', ''cluster'', ''som'' (optional) and ''rgl'' (optional). 
- 
- 
-===== Schedule ===== 
- 
-== Introduction & foundations (Mon, 27 July) == 
- 
-  * general introduction & background 
-  * DSMs in a nutshell 
-  * the DSM parameter space: a taxonomy 
-  
-== Matrix algebra & vector spaces (Tue, 28 July) == 
- 
-  * matrix representation, foundations of matrix algebra 
-  * geometric analysis (norms, distances, similarity & angles) 
-  * implementation: R as an interactive DSM laboratory 
- 
-== Applications of DSMs (Wed, 29 July) == 
- 
-  * What can we do with DSM vectors? 
-  * Do DSMs capture interesting aspects of word meaning? 
- 
-== Manipulating & understanding DSM spaces (Thu, 30 July) == 
- 
-  * more advanced matrix algebra & implementation 
-  * singular value decomposition (SVD) 
-  * managing high-dimensional DSMs (SVD, random indexing) 
-  * visualisation and intuitive interpretation 
-  * mathematical properties of special DSMs 
- 
-== Challenges for DSMs & current research (Fri, 31 July) == 
- 
-  * looking for a unified model 
-  * connection to formal semantics: compositionality, inference, reference 
-  * holographic memory, probabilistic approaches 

You are here: start » course