Distributional Semantic Models (ESSLLI 2009)

Distributional Semantic Models: Theory and empirical results ESSLLI 2009 (Bordeaux)
Advanced course at ESSLLI 2009, Bordeaux, July 27-31, 2009

Course description

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. 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.

Lecturers: Stefan Evert (U Osnabrück), Alessandro Lenci (U Pisa)

Many thanks to all our participants for following this course and staying with us to the very end! We enjoyed the experience very much and hope to keep in touch with you. For this purpose, we're planning to set up a DSM mailing list, where you can exchange ideas, present your own DSM work, discuss possible DSM architectures, etc.

Alfredo Maldonado Guerra has put some photos from our course on his homepage. Thanks, Alfredo! If you have also taken photos and would like to share them, please send an e-mail to stefan.evert@uos.de.