January 2018
Beginner to intermediate
284 pages
8h 35m
English
The very fundamental idea of distributional similarity-based representations is that a word can be represented by the means of its neighbors. As said by J. R. Firth 1957: 11:
This is perhaps one of the most successful ideas of modern statistical NLP. The definition of neighbors can vary to take account of either local or larger contexts to get a more syntactic or semantic representation.
Read now
Unlock full access