Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
course:start [2009/07/15 23:01] schtepf |
course:start [2018/07/26 09:33] schtepf [Schedules & handouts] |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== | + | ====== |
- | **Distributional Semantic Models: | + | These pages provide information, |
- | //Advanced course at [[http://esslli2009.labri.fr/|ESSLLI 2009]], Bordeaux, July 27-31, 2009// | + | |
- | * [[course: | + | ===== Schedules & handouts |
- | * [[course: | + | |
- | * [[course: | + | |
- | ===== Course description ===== | + | * Advanced course on [[course: |
+ | * [[course: | ||
+ | * Introductory course on [[: | ||
- | 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, | + | |
- | This course | + | * [[course: |
+ | * [[course: | ||
- | **Lecturers: | ||
- | |||
- | {{: | ||
- | **Important note: | ||
- | Handouts and other materials for the course will be made available on this Web page and updated during the course. | ||
- | We also plan to provide code examples for constructing and analyzing small-scale DSMs in [[http:// | ||
- | |||
- | |||
- | ===== 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, | ||
- | * geometric analysis (norms, distances, similarity & angles) | ||
- | * implementation: | ||
- | |||
- | == 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, | ||
- | * holographic memory, probabilistic approaches |