Quizz 07: Word Embeddings
This quizz covers material from the sixth lecture on Word Embeddings.
-
Consider the task of predicting the POS tag of a word using a model similar to the one we discussed in class predicting the language
of documents. Given a tagset of dimension T, what would be the task-specific embedding of words the model would learn? What would be
the dimension of the embeddings?
-
List three key properties of word embedding representations which distinguish them from one hot encodings?
-
Explain the intuition behind distributional methods - that is, why do we believe that solving the task of predicting a word
given its context yields embeddings which capture lexical semantics?
Last modified 24 Dec 2017